├── .github ├── .testcoverage.yml ├── ISSUE_TEMPLATE │ ├── 100_feature_request.yml │ ├── 200_bug_report.yml │ └── 300_RFC.yml ├── PULL_REQUEST_TEMPLATE.md └── workflows │ ├── chart-ci.yml │ ├── docker-build-images.yml │ ├── docker-push-images.yml │ ├── installation-tests.yml │ ├── lint-and-tests.yml │ ├── python-aibrix-kvcache-tests.yml │ ├── python-aibrix-tests.yml │ └── release-build.yaml ├── .gitignore ├── .golangci.yml ├── .readthedocs.yaml ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── Makefile ├── PROJECT ├── README.md ├── SECURITY.md ├── api ├── autoscaling │ └── v1alpha1 │ │ ├── groupversion_info.go │ │ ├── podautoscaler_types.go │ │ ├── podautoscaler_types_test.go │ │ └── zz_generated.deepcopy.go ├── model │ └── v1alpha1 │ │ ├── groupversion_info.go │ │ ├── modeladapter_types.go │ │ └── zz_generated.deepcopy.go └── orchestration │ └── v1alpha1 │ ├── condition.go │ ├── groupversion_info.go │ ├── kvcache_types.go │ ├── podset_types.go │ ├── raycluster_type.go │ ├── rayclusterfleet_types.go │ ├── rayclusterreplicaset_types.go │ ├── roleset_types.go │ ├── stormservice_types.go │ └── zz_generated.deepcopy.go ├── benchmarks ├── README.md ├── benchmark.py ├── client │ ├── README.md │ ├── __init__.py │ ├── analyze.py │ ├── client.py │ └── utils.py ├── config.yaml ├── generator │ ├── .gitignore │ ├── __init__.py │ ├── dataset_generator │ │ ├── README.md │ │ ├── __init__.py │ │ ├── converter.py │ │ ├── dataset-examples.png │ │ ├── multiturn_prefix_sharing_dataset.py │ │ ├── synthetic_prefix_sharing_dataset.py │ │ ├── synthetic_prompt.py │ │ ├── util.py │ │ └── utility.py │ └── workload_generator │ │ ├── README.md │ │ ├── __init__.py │ │ ├── config │ │ └── examples │ │ │ ├── completion-len-config.json │ │ │ ├── prompt-len-config.json │ │ │ └── traffic-config.json │ │ ├── distribution.py │ │ ├── sample_request.py │ │ ├── utility.py │ │ ├── utils.py │ │ ├── workload-plot-example.png │ │ └── workload_generator.py ├── image │ ├── aibrix-benchmark-client.png │ ├── aibrix-benchmark-component.png │ ├── aibrix-benchmark-dataset.png │ └── aibrix-benchmark-workload.png ├── plot │ ├── aibrix0.1-downloader.ipynb │ ├── aibrix0.1-lora.ipynb │ ├── aibrix0.1-routing.ipynb │ └── aibrix0.3-routing_vtc-basic-vs-random.ipynb ├── requirements.txt └── scenarios │ ├── autoscaling │ ├── README.md │ ├── deepseek-llm-7b-chat │ │ ├── apa.yaml │ │ ├── deploy.yaml │ │ ├── hpa.yaml │ │ ├── kpa.yaml │ │ ├── optimizer-kpa.yaml │ │ └── svc.yaml │ ├── overnight_run.sh │ ├── plot-everything.py │ ├── plot_per_pod.py │ ├── requirements_bench_pa.txt │ ├── run-test.sh │ ├── workload-configs │ │ └── predefined │ │ │ ├── completion-len-configs │ │ │ ├── HighFast.json │ │ │ ├── HighSlow.json │ │ │ ├── LowFast.json │ │ │ └── LowSlow.json │ │ │ ├── prompt-len-configs │ │ │ ├── HighFast.json │ │ │ ├── HighSlow.json │ │ │ ├── LowFast.json │ │ │ └── LowSlow.json │ │ │ └── traffic-configs │ │ │ ├── HighFast.json │ │ │ ├── HighSlow.json │ │ │ ├── LowFast.json │ │ │ └── LowSlow.json │ └── workload │ │ ├── 25min_up_and_down │ │ ├── 25min_up_and_down.jsonl │ │ └── plot-synthetic-from-csv-file-synthetic2.pdf │ │ ├── 5s.jsonl │ │ ├── 8min_up_and_down.jsonl │ │ ├── one_request.jsonl │ │ └── ten_requests.jsonl │ ├── gateway │ ├── 7b.yaml │ ├── README.md │ ├── benchmark.py │ └── client.py │ ├── kvcache │ └── README.md │ ├── lora │ ├── README.md │ └── benchmark.py │ └── utils │ ├── check_k8s_is_ready.py │ ├── count_num_pods.py │ ├── set_num_replicas.py │ └── streaming_pod_log_to_file.py ├── cmd ├── controllers │ └── main.go ├── kvcache-watcher │ └── main.go └── plugins │ └── main.go ├── config ├── .gitignore ├── crd │ ├── autoscaling │ │ ├── autoscaling.aibrix.ai_podautoscalers.yaml │ │ └── kustomization.yaml │ ├── kustomization.yaml │ ├── kustomizeconfig.yaml │ ├── model │ │ ├── kustomization.yaml │ │ └── model.aibrix.ai_modeladapters.yaml │ └── orchestration │ │ ├── kustomization.yaml │ │ ├── orchestration.aibrix.ai_kvcaches.yaml │ │ ├── orchestration.aibrix.ai_podsets.yaml │ │ ├── orchestration.aibrix.ai_rayclusterfleets.yaml │ │ ├── orchestration.aibrix.ai_rayclusterreplicasets.yaml │ │ ├── orchestration.aibrix.ai_rolesets.yaml │ │ └── orchestration.aibrix.ai_stormservices.yaml ├── default │ ├── kustomization.yaml │ ├── manager_webhook_patch.yaml │ └── webhookcainjection_patch.yaml ├── dependency │ ├── envoy-gateway │ │ ├── envoy_gateway_patch.yaml │ │ └── kustomization.yaml │ ├── kuberay-operator │ │ ├── README.md │ │ ├── crds │ │ │ ├── ray.io_rayclusters.yaml │ │ │ ├── ray.io_rayjobs.yaml │ │ │ └── ray.io_rayservices.yaml │ │ ├── kustomization.yaml │ │ └── templates │ │ │ ├── deployment.yaml │ │ │ ├── leader_election_role.yaml │ │ │ ├── leader_election_role_binding.yaml │ │ │ ├── multiple_namespaces_role.yaml │ │ │ ├── multiple_namespaces_rolebinding.yaml │ │ │ ├── ray_rayjob_editor_role.yaml │ │ │ ├── ray_rayjob_viewer_role.yaml │ │ │ ├── ray_rayservice_editor_role.yaml │ │ │ ├── ray_rayservice_viewer_role.yaml │ │ │ ├── role.yaml │ │ │ ├── rolebinding.yaml │ │ │ ├── service.yaml │ │ │ └── serviceaccount.yaml │ └── kustomization.yaml ├── experimentals │ └── gpu-optimizer │ │ ├── gateway-plugin │ │ └── kustomization.yaml │ │ └── kustomization.yaml ├── gateway │ ├── gateway-plugin │ │ ├── gateway-plugin.yaml │ │ └── kustomization.yaml │ ├── gateway.yaml │ └── kustomization.yaml ├── gpu-optimizer │ ├── deployment.yaml │ ├── kustomization.yaml │ ├── rbac.yaml │ └── service.yaml ├── internalcert │ ├── kustomization.yaml │ └── secret.yaml ├── job │ ├── k8s_job_rbac.yaml │ └── kustomization.yaml ├── manager │ ├── kustomization.yaml │ └── manager.yaml ├── metadata │ ├── job_template_patch.yaml │ ├── kustomization.yaml │ ├── metadata.yaml │ ├── redis.yaml │ ├── s3-env-patch.yaml │ └── tos-env-patch.yaml ├── namespace │ ├── kustomization.yaml │ └── namespace.yaml ├── overlays │ ├── dev │ │ ├── gateway-plugin │ │ │ └── kustomization.yaml │ │ ├── gpu-optimizer │ │ │ └── kustomization.yaml │ │ └── manager │ │ │ └── kustomization.yaml │ ├── release │ │ ├── envoy_proxy_patch.yaml │ │ ├── gateway_plugins_patch.yaml │ │ ├── kustomization.yaml │ │ └── pdb.yaml │ ├── vke-dev │ │ ├── gateway-plugin │ │ │ ├── gateway_plugins_patch.yaml │ │ │ └── kustomization.yaml │ │ ├── gpu-optimizer │ │ │ └── kustomization.yaml │ │ └── manager │ │ │ └── kustomization.yaml │ ├── vke-ipv6 │ │ ├── envoy_proxy_patch.yaml │ │ └── kustomization.yaml │ └── vke │ │ ├── default │ │ ├── envoy_proxy_patch.yaml │ │ ├── gateway_plugins_patch.yaml │ │ └── kustomization.yaml │ │ └── dependency │ │ ├── envoy_gateway_patch.yaml │ │ └── kustomization.yaml ├── prometheus │ ├── kustomization.yaml │ └── monitor.yaml ├── rbac │ ├── autoscaling │ │ ├── autoscaling_podautoscaler_editor_role.yaml │ │ ├── autoscaling_podautoscaler_viewer_role.yaml │ │ └── kustomization.yaml │ ├── controller-manager │ │ ├── kustomization.yaml │ │ ├── leader_election_role.yaml │ │ ├── leader_election_role_binding.yaml │ │ ├── role.yaml │ │ ├── role_binding.yaml │ │ └── service_account_controller_manager.yaml │ ├── gateway │ │ ├── kustomization.yaml │ │ ├── role_binding_gateway.yaml │ │ ├── role_gateway.yaml │ │ └── service_account_gateway.yaml │ ├── kustomization.yaml │ ├── model │ │ ├── kustomization.yaml │ │ ├── model_modeladapter_editor_role.yaml │ │ └── model_modeladapter_viewer_role.yaml │ └── orchestration │ │ ├── kustomization.yaml │ │ ├── orchestration_kvcache_editor_role.yaml │ │ ├── orchestration_kvcache_viewer_role.yaml │ │ ├── orchestration_rayclusterfleet_editor_role.yaml │ │ ├── orchestration_rayclusterfleet_viewer_role.yaml │ │ ├── orchestration_rayclusterreplicaset_editor_role.yaml │ │ ├── orchestration_rayclusterreplicaset_viewer_role.yaml │ │ ├── orchestration_roleset_editor_role.yaml │ │ ├── orchestration_roleset_viewer_role.yaml │ │ ├── orchestration_stormservice_editor_role.yaml │ │ └── orchestration_stormservice_viewer_role.yaml ├── samples │ ├── autoscaling_v1alpha1_demo_nginx.yaml │ ├── autoscaling_v1alpha1_kpa.yaml │ ├── autoscaling_v1alpha1_mock_llama.yaml │ ├── autoscaling_v1alpha1_mock_llama_apa.yaml │ ├── autoscaling_v1alpha1_podautoscaler.yaml │ ├── kustomization.yaml │ ├── model_v1alpha1_modeladapter.yaml │ ├── orchestration_v1alpha1_kvcache.yaml │ ├── orchestration_v1alpha1_rayclusterfleet.yaml │ ├── orchestration_v1alpha1_rayclusterreplicaset.yaml │ ├── orchestration_v1alpha1_roleset.yaml │ └── orchestration_v1alpha1_stormservice.yaml ├── standalone │ ├── autoscaler-controller │ │ ├── kustomization.yaml │ │ └── patch.yaml │ ├── distributed-inference-controller │ │ ├── kustomization.yaml │ │ └── patch.yaml │ ├── kv-cache-controller │ │ ├── kustomization.yaml │ │ └── patch.yaml │ ├── model-adapter-controller │ │ ├── kustomization.yaml │ │ └── patch.yaml │ └── stormservice-controller │ │ ├── kustomization.yaml │ │ └── patch.yaml ├── test │ ├── README.md │ ├── gateway │ │ ├── kustomization.yaml │ │ └── vtc-test-env-patch.yaml │ └── kustomization.yaml └── webhook │ ├── kustomization.yaml │ ├── kustomizeconfig.yaml │ ├── manifests.yaml │ └── service.yaml ├── deployment └── terraform │ ├── .gitignore │ ├── gcp │ ├── .terraform-docs.yml │ ├── .terraform.lock.hcl │ ├── README.md │ ├── cluster │ │ ├── data.tf │ │ ├── main.tf │ │ ├── outputs.tf │ │ ├── terraform.tf │ │ └── variables.tf │ ├── data.tf │ ├── docs.md │ ├── locals.tf │ ├── main.tf │ ├── outputs.tf │ ├── providers.tf │ ├── terraform.tf │ ├── terraform.tfvars.example │ └── variables.tf │ ├── go.mod │ ├── go.sum │ ├── kubernetes │ ├── .terraform.lock.hcl │ ├── README.md │ ├── data.tf │ ├── locals.tf │ ├── main.tf │ ├── outputs.tf │ ├── terraform.tf │ └── variables.tf │ └── tests │ └── gcp_test.go ├── development ├── README.md ├── app │ ├── Dockerfile │ ├── Makefile │ ├── README.md │ ├── app.py │ ├── config.json │ ├── config │ │ ├── heterogeneous │ │ │ ├── kustomization.yaml │ │ │ └── simulator_a40 │ │ │ │ ├── kustomization.yaml │ │ │ │ ├── patch_deployment_a40.yaml │ │ │ │ ├── patch_podautoscaler_a40.yaml │ │ │ │ ├── rename_deployment_a40.json │ │ │ │ └── rename_podautoscaler_a40.json │ │ ├── mock │ │ │ ├── api-key-patch.yaml │ │ │ ├── components.yaml │ │ │ └── kustomization.yaml │ │ ├── simulator │ │ │ ├── kustomization.yaml │ │ │ ├── patch_deployment_a100.yaml │ │ │ ├── patch_podautoscaler_a100.yaml │ │ │ ├── rename_deployment_a100.json │ │ │ └── rename_podautoscaler_a100.json │ │ ├── templates │ │ │ ├── deployment │ │ │ │ ├── deployment.yaml │ │ │ │ └── kustomization.yaml │ │ │ └── podautoscaler │ │ │ │ ├── kustomization.yaml │ │ │ │ ├── podautoscaler_apa.yaml │ │ │ │ ├── podautoscaler_hpa.yaml │ │ │ │ └── podautoscaler_kpa.yaml │ │ └── vke │ │ │ └── kustomization.yaml │ ├── entrypoint.sh │ ├── requirements.txt │ ├── simulator.py │ ├── test_app.py │ └── zscaler_root_ca.crt ├── tutorials │ ├── batch │ │ └── README.md │ ├── distributed │ │ ├── README.md │ │ ├── fleet-autoscaling.yaml │ │ ├── fleet-mock.yaml │ │ ├── fleet.yaml │ │ ├── nvkind-single-node.yaml │ │ ├── nvkind-two-nodes.yaml │ │ ├── raycluster-head-no-gpu.yaml │ │ ├── raycluster.yaml │ │ └── rayjob.yaml │ ├── kvcache │ │ └── kvcache.yaml │ ├── lora │ │ ├── README.md │ │ ├── deployment.yaml │ │ ├── model_adapter.yaml │ │ └── model_adapter_api_key.yaml │ ├── metrics │ │ └── service-monitor.yaml │ ├── podautoscaler │ │ ├── README.md │ │ ├── hpa.yaml │ │ └── pa.yaml │ └── runtime │ │ ├── README.md │ │ ├── runtime-hf-download.yaml │ │ ├── runtime-s3-download.yaml │ │ └── runtime-tos-download.yaml └── vllm │ ├── README.md │ ├── kind-config.yaml │ ├── linux │ └── kustomization.yaml │ └── macos │ ├── components.yaml │ ├── deployment.yaml │ └── kustomization.yaml ├── dist └── chart │ ├── .helmignore │ ├── Chart.yaml │ ├── README.md │ ├── crds │ ├── autoscaling.aibrix.ai_podautoscalers.yaml │ ├── model.aibrix.ai_modeladapters.yaml │ ├── orchestration.aibrix.ai_kvcaches.yaml │ ├── orchestration.aibrix.ai_podsets.yaml │ ├── orchestration.aibrix.ai_rayclusterfleets.yaml │ ├── orchestration.aibrix.ai_rayclusterreplicasets.yaml │ ├── orchestration.aibrix.ai_rolesets.yaml │ └── orchestration.aibrix.ai_stormservices.yaml │ ├── stable.yaml │ ├── templates │ ├── _helpers.tpl │ ├── controller-manager │ │ ├── deployment.yaml │ │ ├── rbac.yaml │ │ └── service.yaml │ ├── gateway-instance │ │ └── gateway.yaml │ ├── gateway-plugin │ │ ├── deployment.yaml │ │ ├── envoy_extension_policy.yaml │ │ ├── httproute.yaml │ │ ├── rbac.yaml │ │ └── service.yaml │ ├── gpu-optimizer │ │ ├── deployment.yaml │ │ ├── rbac.yaml │ │ └── service.yaml │ ├── metadata-service │ │ ├── deployment.yaml │ │ ├── rbac.yaml │ │ ├── redis.yaml │ │ └── service.yaml │ ├── prometheus │ │ └── monitor.yaml │ └── webhook │ │ ├── secret.yaml │ │ ├── service.yaml │ │ └── webhooks.yaml │ ├── values.schema.json │ ├── values.yaml │ └── vke.yaml ├── docs ├── .gitattributes ├── Makefile ├── README.md ├── kv-event-sync-readme.md ├── make.bat ├── paper │ └── AIBrix_White_Paper_0219_2025.pdf ├── requirements-docs.txt └── source │ ├── assets │ ├── images │ │ ├── ai-engine-runtime-overview.png │ │ ├── aibrix-architecture-v1.jpeg │ │ ├── aibrix-dist-kv-cache-arch-overview.png │ │ ├── aibrix-dist-kv-cache-dashboard.png │ │ ├── aibrix-infinistore-arch-overview.png │ │ ├── aibrix-kvcache-offloading-arch-overview.png │ │ ├── aibrix-kvcache-profiling.png │ │ ├── autoscaler │ │ │ ├── aibrix-controller-manager-output.png │ │ │ ├── autoscaling_result.png │ │ │ ├── optimizer-based-autoscaling-70-results.png │ │ │ ├── optimizer-based-podautoscaler.png │ │ │ └── podautoscaler-describe.png │ │ ├── benchmark │ │ │ └── aibrix-benchmark-component-doc.png │ │ ├── cloud │ │ │ ├── lambda-cloud-installation.png │ │ │ ├── lambda-cloud-instance.png │ │ │ ├── lambda-cloud-ssh.png │ │ │ └── lambda-cloud-verify-installation.png │ │ ├── delete-namespace-stuck-1.png │ │ ├── delete-namespace-stuck-2.png │ │ ├── draft-release.png │ │ ├── gateway-design.png │ │ ├── heterogeneous-gpu-diagram.png │ │ ├── lora-controller-workflow.png │ │ ├── lora-sequence-diagram.png │ │ ├── lora-service-discovery-resources.png │ │ ├── mix-grain-orchestration.png │ │ ├── model-error.png │ │ ├── release-pipeline-manifests.png │ │ ├── release-pipeline-python-package.png │ │ ├── slo_routing │ │ │ ├── evaluation.png │ │ │ ├── motivation.png │ │ │ └── variation_comparison.png │ │ └── stormservice │ │ │ └── aibrix-stormservice-illustration.png │ └── logos │ │ └── aibrix-logo.jpeg │ ├── community │ ├── community.rst │ ├── contribution.rst │ └── research.rst │ ├── conf.py │ ├── designs │ ├── aibrix-autoscaler.rst │ ├── aibrix-engine-runtime.rst │ ├── aibrix-kvcache-offloading-framework.rst │ ├── aibrix-router.rst │ ├── aibrix-stormservice.rst │ └── architecture.rst │ ├── development │ ├── development.rst │ └── release.rst │ ├── features │ ├── autoscaling │ │ ├── autoscaling.rst │ │ ├── metric-based-autoscaling.rst │ │ └── optimizer-based-autoscaling.rst │ ├── batch-api.rst │ ├── benchmark-and-generator.rst │ ├── gateway-plugins.rst │ ├── heterogeneous-gpu.rst │ ├── kv-event-sync.rst │ ├── kvcache-offloading.rst │ ├── lora-dynamic-loading.rst │ ├── multi-engine.rst │ ├── multi-node-inference.rst │ └── runtime.rst │ ├── getting_started │ ├── advanced-k8s-examples.rst │ ├── container-images.rst │ ├── faq.rst │ ├── installation │ │ ├── aws.rst │ │ ├── gcp.rst │ │ ├── installation.rst │ │ ├── lambda.rst │ │ ├── mac-for-desktop.rst │ │ └── vke.rst │ └── quickstart.rst │ ├── index.rst │ └── production │ └── observability.rst ├── go.mod ├── go.sum ├── hack ├── boilerplate.go.txt ├── ci │ └── kind-config.yaml ├── enable-kv-events.sh ├── lambda-cloud │ ├── README.md │ ├── install.sh │ ├── nvkind-cluster.yaml │ ├── setup.sh │ └── verify.sh ├── rdma │ ├── detect-gid-in-container.sh │ └── search-gid.sh ├── release │ ├── sync-dependency-images.sh │ └── sync-images.sh ├── tools.go ├── update-codegen.sh ├── verify-codegen.sh └── verify-crd-sync.sh ├── observability ├── grafana │ ├── AIBrix_Control_Plane_Runtime_Dashboard.json │ ├── AIBrix_Envoy_Gateway_Dashboard.json │ ├── AIBrix_Envoy_Gateway_Plugins_Dashboard.json │ └── AIBrix_vLLM_Engine_Dashboard.json └── monitor │ ├── envoy_metrics_service.yaml │ ├── service_monitor_controller_manager.yaml │ ├── service_monitor_gateway.yaml │ ├── service_monitor_gateway_plugin.yaml │ └── service_monitor_vllm.yaml ├── pkg ├── cache │ ├── README.md │ ├── build_verification_default_test.go │ ├── build_verification_zmq_test.go │ ├── cache_api.go │ ├── cache_impl.go │ ├── cache_init.go │ ├── cache_init_test.go │ ├── cache_log.go │ ├── cache_metrics.go │ ├── cache_profile.go │ ├── cache_test.go │ ├── cache_trace.go │ ├── errors.go │ ├── informers.go │ ├── kv_event_manager.go │ ├── kv_event_manager_validation_test.go │ ├── kv_event_manager_zmq.go │ ├── kvcache │ │ ├── README.md │ │ ├── endpoint.go │ │ ├── endpoint_test.go │ │ ├── event_types.go │ │ ├── metrics.go │ │ ├── metrics_test.go │ │ ├── msgpack_decoder.go │ │ ├── msgpack_decoder_test.go │ │ ├── msgpack_encoder.go │ │ ├── types.go │ │ ├── zmq_client.go │ │ ├── zmq_client_stub.go │ │ └── zmq_client_test.go │ ├── load_provider.go │ ├── model.go │ ├── model_gpu_profile.go │ ├── model_gpu_profile_test.go │ ├── output_predictor.go │ ├── output_predictor_test.go │ ├── pending_load_provider.go │ ├── pod.go │ ├── store_providers.go │ ├── store_providers_test.go │ ├── test_helpers.go │ ├── trace.go │ ├── trace_test.go │ └── utils.go ├── cert │ └── cert.go ├── client │ ├── applyconfiguration │ │ ├── autoscaling │ │ │ └── v1alpha1 │ │ │ │ ├── metricsource.go │ │ │ │ ├── podautoscaler.go │ │ │ │ ├── podautoscalerspec.go │ │ │ │ ├── podautoscalerstatus.go │ │ │ │ ├── scalingdecision.go │ │ │ │ └── subtargetselector.go │ │ ├── internal │ │ │ └── internal.go │ │ ├── model │ │ │ └── v1alpha1 │ │ │ │ ├── modeladapter.go │ │ │ │ ├── modeladapterspec.go │ │ │ │ └── modeladapterstatus.go │ │ ├── orchestration │ │ │ └── v1alpha1 │ │ │ │ ├── condition.go │ │ │ │ ├── coschedulingschedulingstrategyspec.go │ │ │ │ ├── disruptiontolerance.go │ │ │ │ ├── godelschedulingstrategyspec.go │ │ │ │ ├── rayclusterfleet.go │ │ │ │ ├── rayclusterfleetcondition.go │ │ │ │ ├── rayclusterfleetspec.go │ │ │ │ ├── rayclusterfleetstatus.go │ │ │ │ ├── rayclusterreplicaset.go │ │ │ │ ├── rayclusterreplicasetspec.go │ │ │ │ ├── rayclusterreplicasetstatus.go │ │ │ │ ├── rayclustertemplatespec.go │ │ │ │ ├── rolesetspec.go │ │ │ │ ├── rolesettemplatespec.go │ │ │ │ ├── rolespec.go │ │ │ │ ├── rolestatus.go │ │ │ │ ├── roleupdatestrategy.go │ │ │ │ ├── schedulingstrategy.go │ │ │ │ ├── stormservice.go │ │ │ │ ├── stormservicespec.go │ │ │ │ ├── stormservicestatus.go │ │ │ │ ├── stormserviceupdatestrategy.go │ │ │ │ └── volcanoschedulingstrategyspec.go │ │ └── utils.go │ ├── clientset │ │ └── versioned │ │ │ ├── clientset.go │ │ │ ├── fake │ │ │ ├── clientset_generated.go │ │ │ ├── doc.go │ │ │ └── register.go │ │ │ ├── scheme │ │ │ ├── doc.go │ │ │ └── register.go │ │ │ └── typed │ │ │ ├── autoscaling │ │ │ └── v1alpha1 │ │ │ │ ├── autoscaling_client.go │ │ │ │ ├── doc.go │ │ │ │ ├── fake │ │ │ │ ├── doc.go │ │ │ │ ├── fake_autoscaling_client.go │ │ │ │ └── fake_podautoscaler.go │ │ │ │ ├── generated_expansion.go │ │ │ │ └── podautoscaler.go │ │ │ ├── model │ │ │ └── v1alpha1 │ │ │ │ ├── doc.go │ │ │ │ ├── fake │ │ │ │ ├── doc.go │ │ │ │ ├── fake_model_client.go │ │ │ │ └── fake_modeladapter.go │ │ │ │ ├── generated_expansion.go │ │ │ │ ├── model_client.go │ │ │ │ └── modeladapter.go │ │ │ └── orchestration │ │ │ └── v1alpha1 │ │ │ ├── doc.go │ │ │ ├── fake │ │ │ ├── doc.go │ │ │ ├── fake_orchestration_client.go │ │ │ ├── fake_rayclusterfleet.go │ │ │ ├── fake_rayclusterreplicaset.go │ │ │ └── fake_stormservice.go │ │ │ ├── generated_expansion.go │ │ │ ├── orchestration_client.go │ │ │ ├── rayclusterfleet.go │ │ │ ├── rayclusterreplicaset.go │ │ │ └── stormservice.go │ ├── informers │ │ └── externalversions │ │ │ ├── autoscaling │ │ │ ├── interface.go │ │ │ └── v1alpha1 │ │ │ │ ├── interface.go │ │ │ │ └── podautoscaler.go │ │ │ ├── factory.go │ │ │ ├── generic.go │ │ │ ├── internalinterfaces │ │ │ └── factory_interfaces.go │ │ │ ├── model │ │ │ ├── interface.go │ │ │ └── v1alpha1 │ │ │ │ ├── interface.go │ │ │ │ └── modeladapter.go │ │ │ └── orchestration │ │ │ ├── interface.go │ │ │ └── v1alpha1 │ │ │ ├── interface.go │ │ │ ├── rayclusterfleet.go │ │ │ ├── rayclusterreplicaset.go │ │ │ └── stormservice.go │ └── listers │ │ ├── autoscaling │ │ └── v1alpha1 │ │ │ ├── expansion_generated.go │ │ │ └── podautoscaler.go │ │ ├── model │ │ └── v1alpha1 │ │ │ ├── expansion_generated.go │ │ │ └── modeladapter.go │ │ └── orchestration │ │ └── v1alpha1 │ │ ├── expansion_generated.go │ │ ├── rayclusterfleet.go │ │ ├── rayclusterreplicaset.go │ │ └── stormservice.go ├── config │ └── config.go ├── constants │ ├── kv_event_sync.go │ ├── kvcache.go │ ├── metrics.go │ └── model.go ├── controller │ ├── constants │ │ └── stormservice.go │ ├── controller.go │ ├── kvcache │ │ ├── backends │ │ │ ├── common.go │ │ │ ├── common_test.go │ │ │ ├── distributed.go │ │ │ ├── distributed_test.go │ │ │ ├── hpkv.go │ │ │ ├── hpkv_test.go │ │ │ ├── infinistore.go │ │ │ ├── infinistore_test.go │ │ │ ├── reconciler.go │ │ │ └── vineyard.go │ │ ├── kvcache_controller.go │ │ ├── kvcache_controller_ginkgo_test.go │ │ ├── kvcache_controller_test.go │ │ └── suite_test.go │ ├── modeladapter │ │ ├── README.md │ │ ├── modeladapter_controller.go │ │ ├── modeladapter_controller_test.go │ │ ├── modeladapter_controller_unit_tests.go │ │ ├── resources.go │ │ ├── resources_test.go │ │ ├── scheduling │ │ │ ├── bin_pack.go │ │ │ ├── least_adapters.go │ │ │ ├── least_latency.go │ │ │ ├── least_throughput.go │ │ │ ├── random.go │ │ │ └── scheduler.go │ │ ├── suite_test.go │ │ ├── utils.go │ │ └── utils_test.go │ ├── modelrouter │ │ ├── modelrouter_controller.go │ │ └── modelrouter_controller_test.go │ ├── podautoscaler │ │ ├── aggregation │ │ │ └── aggregator.go │ │ ├── algorithm │ │ │ ├── algorithm.go │ │ │ ├── apa.go │ │ │ ├── apa_test.go │ │ │ ├── hpa.go │ │ │ ├── kpa.go │ │ │ ├── kpa_test.go │ │ │ └── mock_context_test.go │ │ ├── autoscaler.go │ │ ├── autoscaler_test.go │ │ ├── context │ │ │ ├── context.go │ │ │ └── context_test.go │ │ ├── hpa_resources.go │ │ ├── hpa_resources_test.go │ │ ├── metrics │ │ │ ├── client.go │ │ │ ├── client_test.go │ │ │ ├── collector.go │ │ │ ├── fetcher.go │ │ │ ├── fetcher_test.go │ │ │ └── utils.go │ │ ├── monitor │ │ │ ├── metrics.go │ │ │ ├── monitor.go │ │ │ └── monitor_test.go │ │ ├── podautoscaler_controller.go │ │ ├── podautoscaler_controller_test.go │ │ ├── types │ │ │ ├── annotations.go │ │ │ ├── core.go │ │ │ ├── metrics.go │ │ │ └── metrics_test.go │ │ ├── utils.go │ │ ├── workload_scale.go │ │ └── workload_scale_test.go │ ├── podset │ │ └── podset_controller.go │ ├── rayclusterfleet │ │ ├── progress.go │ │ ├── rayclusterfleet_controller.go │ │ ├── rayclusterfleet_controller_test.go │ │ ├── recreate.go │ │ ├── rollback.go │ │ ├── rolling.go │ │ ├── suite_test.go │ │ ├── sync.go │ │ └── util │ │ │ └── fleet.go │ ├── rayclusterreplicaset │ │ ├── rayclusterreplicaset_controller.go │ │ ├── rayclusterreplicaset_controller_test.go │ │ ├── rayclusterreplicaset_utils.go │ │ └── suite_test.go │ ├── roleset │ │ ├── podset_rollsyncer.go │ │ ├── roleset_controller.go │ │ ├── roleset_controller_test.go │ │ ├── rolesyncer.go │ │ ├── rolesyncer_test.go │ │ ├── rolling.go │ │ ├── suite_test.go │ │ ├── sync.go │ │ ├── utils.go │ │ └── utils_test.go │ ├── stormservice │ │ ├── revision.go │ │ ├── revision_test.go │ │ ├── rolesetoperations.go │ │ ├── rolesetoperations_test.go │ │ ├── stormservice_controller.go │ │ ├── stormservice_controller_test.go │ │ ├── suite_test.go │ │ ├── sync.go │ │ ├── sync_test.go │ │ ├── utils.go │ │ └── utils_test.go │ └── util │ │ ├── controller_utils.go │ │ ├── controller_utils_test.go │ │ ├── expectation │ │ ├── expectation.go │ │ └── expectation_test.go │ │ ├── history │ │ └── controller_history.go │ │ ├── orchestration │ │ ├── util.go │ │ └── util_test.go │ │ └── patch │ │ ├── json_patch.go │ │ ├── json_patch_test.go │ │ ├── patch_method.go │ │ └── patch_method_test.go ├── features │ └── features.go ├── kvevent │ ├── doc.go │ ├── errors.go │ ├── handler.go │ ├── handler_test.go │ ├── integration_test.go │ ├── interfaces.go │ ├── manager.go │ ├── manager_comprehensive_test.go │ ├── manager_test.go │ └── test_helpers.go ├── metrics │ ├── common.go │ ├── custom_metrics.go │ ├── custom_metrics_test.go │ ├── engine_fetcher.go │ ├── engine_fetcher_test.go │ ├── metrics.go │ ├── server.go │ ├── types.go │ ├── types_test.go │ ├── utils.go │ └── utils_test.go ├── plugins │ └── gateway │ │ ├── algorithms │ │ ├── README.md │ │ ├── algorithms_test.go │ │ ├── fallback.go │ │ ├── fallback_test.go │ │ ├── least_busy_time.go │ │ ├── least_busy_time_test.go │ │ ├── least_gpu_cache.go │ │ ├── least_gpu_cache_test.go │ │ ├── least_kv_cache.go │ │ ├── least_kv_cache_test.go │ │ ├── least_latency.go │ │ ├── least_latency_test.go │ │ ├── least_load.go │ │ ├── least_load_test.go │ │ ├── least_request.go │ │ ├── least_request_test.go │ │ ├── least_util.go │ │ ├── least_util_test.go │ │ ├── model_router_factory.go │ │ ├── pack_load.go │ │ ├── pd_disaggregation.go │ │ ├── pd_disaggregation_test.go │ │ ├── prefix_cache.go │ │ ├── prefix_cache_metrics_test.go │ │ ├── prefix_cache_new_test.go │ │ ├── prefix_cache_preble.go │ │ ├── prefix_cache_preble_test.go │ │ ├── prefix_cache_routing_test.go │ │ ├── prefix_cache_test.go │ │ ├── queue_router.go │ │ ├── random.go │ │ ├── router.go │ │ ├── router_test.go │ │ ├── simple_session_affinity.go │ │ ├── simple_session_affinity_test.go │ │ ├── slo.go │ │ ├── slo_test.go │ │ ├── throughput.go │ │ ├── throughput_test.go │ │ ├── tokenizer_pool.go │ │ ├── tokenizer_pool_metrics_test.go │ │ ├── tokenizer_pool_test.go │ │ ├── util.go │ │ ├── vtc.go │ │ └── vtc │ │ │ ├── token_estimator.go │ │ │ ├── token_estimator_test.go │ │ │ ├── token_tracker.go │ │ │ ├── token_tracker_test.go │ │ │ ├── vtc_basic.go │ │ │ ├── vtc_basic_test.go │ │ │ └── vtc_router.go │ │ ├── gateway.go │ │ ├── gateway_ratelimit.go │ │ ├── gateway_req_body.go │ │ ├── gateway_req_body_test.go │ │ ├── gateway_req_headers.go │ │ ├── gateway_req_headers_test.go │ │ ├── gateway_rsp_body.go │ │ ├── gateway_rsp_headers.go │ │ ├── gateway_rsp_headers_test.go │ │ ├── gateway_test.go │ │ ├── gateway_test_helpers.go │ │ ├── queue │ │ ├── queue_test.go │ │ ├── simple_queue.go │ │ ├── simple_queue_test.go │ │ └── slo_queue.go │ │ ├── ratelimiter │ │ ├── rate_limiter.go │ │ └── redis.go │ │ ├── types.go │ │ ├── util.go │ │ └── util_test.go ├── types │ ├── output_predictor.go │ ├── pod_list.go │ ├── router.go │ ├── router_context.go │ ├── router_context_test.go │ ├── router_queue.go │ └── types_test.go ├── utils │ ├── annotations.go │ ├── annotations_test.go │ ├── hash │ │ ├── hash.go │ │ └── hash_test.go │ ├── kvcache.go │ ├── kvcache_test.go │ ├── labels.go │ ├── labels_test.go │ ├── lrustore │ │ ├── lru_store.go │ │ ├── lru_store_test.go │ │ └── store.go │ ├── modeladapter.go │ ├── modeladapter_test.go │ ├── pod.go │ ├── pod_array.go │ ├── pod_array_test.go │ ├── pod_test.go │ ├── prefixcacheindexer │ │ ├── hash.go │ │ ├── hash_test.go │ │ ├── tree.go │ │ └── tree_test.go │ ├── raycluster.go │ ├── redis.go │ ├── registry.go │ ├── registry_test.go │ ├── sync_map.go │ ├── sync_map_test.go │ ├── syncprefixcacheindexer │ │ ├── README.md │ │ ├── events.go │ │ ├── sync_hash.go │ │ ├── sync_hash_bench_test.go │ │ ├── sync_hash_stress_test.go │ │ └── sync_hash_test.go │ ├── tokenizer │ │ ├── README.md │ │ ├── adapter_sglang.go │ │ ├── adapter_vllm.go │ │ ├── errors.go │ │ ├── interfaces.go │ │ ├── local_characters.go │ │ ├── local_tiktoken.go │ │ ├── remote_client.go │ │ ├── remote_client_test.go │ │ ├── remote_tokenizer.go │ │ ├── tokenizer.go │ │ ├── types.go │ │ └── utils.go │ ├── users.go │ ├── util.go │ ├── util_test.go │ └── utils_test.go └── webhook │ ├── deployment_webhook.go │ ├── kvcache_webhook.go │ ├── modeladapter_webhook.go │ ├── podautoscaler_webhook.go │ ├── sidecar_injection.go │ └── stormservice_webhook.go ├── python ├── aibrix │ ├── README.md │ ├── aibrix │ │ ├── __init__.py │ │ ├── __version__.py │ │ ├── app.py │ │ ├── batch │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── constant.py │ │ │ ├── driver.py │ │ │ ├── job_driver.py │ │ │ ├── job_entity │ │ │ │ ├── __init__.py │ │ │ │ ├── batch_job.py │ │ │ │ ├── job_entity_manager.py │ │ │ │ └── k8s_transformer.py │ │ │ ├── job_manager.py │ │ │ ├── job_progress_manager.py │ │ │ ├── scheduler.py │ │ │ ├── storage │ │ │ │ ├── __init__.py │ │ │ │ ├── adapter.py │ │ │ │ ├── batch_metastore.py │ │ │ │ └── batch_storage.py │ │ │ └── worker.py │ │ ├── common │ │ │ ├── __init__.py │ │ │ └── errors.py │ │ ├── config.py │ │ ├── downloader │ │ │ ├── __init__.py │ │ │ ├── __main__.py │ │ │ ├── base.py │ │ │ ├── entity.py │ │ │ ├── huggingface.py │ │ │ ├── s3.py │ │ │ ├── tos.py │ │ │ └── utils.py │ │ ├── envs.py │ │ ├── gpu_optimizer │ │ │ ├── Makefile │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── app.py │ │ │ ├── load_monitor │ │ │ │ ├── __init__.py │ │ │ │ ├── clusterer.py │ │ │ │ ├── helpers.py │ │ │ │ ├── load_reader.py │ │ │ │ ├── monitor.py │ │ │ │ ├── profile_reader.py │ │ │ │ └── visualizer.py │ │ │ ├── optimizer │ │ │ │ ├── __init__.py │ │ │ │ ├── optimizer.py │ │ │ │ ├── profiling │ │ │ │ │ ├── README.md │ │ │ │ │ ├── benchmark.py │ │ │ │ │ ├── benchmark.sh │ │ │ │ │ ├── gen_benchmark_prompt.py │ │ │ │ │ ├── gen_profile.py │ │ │ │ │ ├── gpu_benchmark.py │ │ │ │ │ └── result │ │ │ │ │ │ ├── simulator-llama2-7b-a100.json │ │ │ │ │ │ ├── simulator-llama2-7b-a100.jsonl │ │ │ │ │ │ ├── simulator-llama2-7b-a100_obsoleted_v1.json │ │ │ │ │ │ ├── simulator-llama2-7b-a40.json │ │ │ │ │ │ └── simulator-llama2-7b-a40.jsonl │ │ │ │ ├── solver │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── melange │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── config_example.json │ │ │ │ │ │ ├── example.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── runner.py │ │ │ │ │ │ ├── solver.py │ │ │ │ │ │ └── util.py │ │ │ │ └── types.py │ │ │ └── utils │ │ │ │ ├── __init__.py │ │ │ │ └── logging.py │ │ ├── logger.py │ │ ├── metadata │ │ │ ├── __init__.py │ │ │ ├── api │ │ │ │ ├── __init__.py │ │ │ │ └── v1 │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── batch.py │ │ │ │ │ ├── files.py │ │ │ │ │ ├── models.py │ │ │ │ │ └── users.py │ │ │ ├── app.py │ │ │ ├── cache │ │ │ │ ├── __init__.py │ │ │ │ ├── job.py │ │ │ │ └── utils.py │ │ │ ├── core │ │ │ │ ├── __init__.py │ │ │ │ ├── asyncio_thread.py │ │ │ │ ├── httpx_client.py │ │ │ │ └── kopf_operator.py │ │ │ ├── secret_gen.py │ │ │ └── setting │ │ │ │ ├── __init__.py │ │ │ │ ├── config.py │ │ │ │ ├── k8s_job_redis_patch.yaml │ │ │ │ ├── k8s_job_s3_patch.yaml │ │ │ │ ├── k8s_job_template.yaml │ │ │ │ ├── k8s_job_tos_patch.yaml │ │ │ │ ├── s3_secret_template.yaml │ │ │ │ └── tos_secret_template.yaml │ │ ├── metrics │ │ │ ├── __init__.py │ │ │ ├── engine_rules.py │ │ │ ├── http_collector.py │ │ │ ├── metrics.py │ │ │ └── standard_rules.py │ │ ├── openapi │ │ │ ├── __init__.py │ │ │ ├── engine │ │ │ │ ├── __init__.py │ │ │ │ ├── base.py │ │ │ │ └── vllm.py │ │ │ ├── model.py │ │ │ └── protocol.py │ │ ├── protos │ │ │ └── __init__.py │ │ ├── runtime │ │ │ ├── __init__.py │ │ │ ├── artifact_service.py │ │ │ └── downloaders.py │ │ └── storage │ │ │ ├── __init__.py │ │ │ ├── base.py │ │ │ ├── factory.py │ │ │ ├── local.py │ │ │ ├── reader.py │ │ │ ├── redis.py │ │ │ ├── s3.py │ │ │ ├── tos.py │ │ │ ├── types.py │ │ │ └── utils.py │ ├── poetry.lock │ ├── pyproject.toml │ ├── scripts │ │ ├── __init__.py │ │ ├── format.sh │ │ └── generate_secrets.py │ └── tests │ │ ├── __init__.py │ │ ├── batch │ │ ├── __init__.py │ │ ├── conftest.py │ │ ├── test_batch_endpoints.py │ │ ├── test_batch_storage_adapter.py │ │ ├── test_driver.py │ │ ├── test_e2e_abnormal_job_behavior.py │ │ ├── test_e2e_openai_batch_api.py │ │ ├── test_inference_client_integration.py │ │ ├── test_job_cache.py │ │ ├── test_job_entity.py │ │ ├── test_job_manager.py │ │ ├── test_k8s_job_persistence.py │ │ ├── test_k8s_job_transformer.py │ │ ├── test_rbac_setup.py │ │ ├── test_worker_s3_integration.py │ │ └── testdata │ │ │ ├── job_rbac.yaml │ │ │ ├── k8s_job_patch_unittest.yaml │ │ │ ├── s3_secret.yaml │ │ │ └── sample_job_input.jsonl │ │ ├── downloader │ │ ├── __init__.py │ │ ├── test_downloader_hf.py │ │ ├── test_downloader_s3.py │ │ ├── test_downloader_tos.py │ │ ├── test_downloader_tos_v1.py │ │ ├── test_entity.py │ │ └── test_utils.py │ │ ├── e2e │ │ ├── README.md │ │ ├── __init__.py │ │ └── test_batch_api.py │ │ ├── gpu_optimizer │ │ ├── __init__.py │ │ ├── test_datasetloadreader.py │ │ ├── test_gatewayloadreader.py │ │ └── test_gen_benchmark.py │ │ ├── metadata │ │ ├── test_app_integration.py │ │ ├── test_kopf_integration.py │ │ ├── test_models_api.py │ │ ├── test_secret_gen.py │ │ └── test_users_api.py │ │ ├── metrics │ │ ├── __init__.py │ │ ├── test_metrics.py │ │ ├── test_metrics_multi_engine.py │ │ └── test_metrics_passthrough_mode.py │ │ ├── openapi │ │ ├── __init__.py │ │ └── engine │ │ │ ├── __init__.py │ │ │ └── test_vllm_engine_lora_loading.py │ │ ├── storage │ │ ├── README.md │ │ ├── __init__.py │ │ ├── conftest.py │ │ ├── test_factory.py │ │ ├── test_local_storage.py │ │ ├── test_reader.py │ │ ├── test_redis_storage.py │ │ ├── test_s3_demo.py │ │ ├── test_storage.py │ │ └── test_utils.py │ │ ├── test_files_api.py │ │ └── test_logger.py └── aibrix_kvcache │ ├── .gitignore │ ├── .pre-commit-config.yaml │ ├── CMakeLists.txt │ ├── LICENSE │ ├── README.md │ ├── aibrix_kvcache │ ├── __init__.py │ ├── _custom_ops.py │ ├── cache_args.py │ ├── cache_handle.py │ ├── cache_hashable.py │ ├── cache_manager.py │ ├── common │ │ ├── __init__.py │ │ ├── absl_logging.py │ │ ├── async_base.py │ │ ├── cached_pyobject.py │ │ ├── object_pool.py │ │ └── threading.py │ ├── config.py │ ├── envs.py │ ├── l1 │ │ ├── __init__.py │ │ ├── eviction_policy │ │ │ ├── __init__.py │ │ │ ├── base_eviction_policy.py │ │ │ ├── fifo.py │ │ │ ├── lru.py │ │ │ └── s3fifo.py │ │ └── l1_cache.py │ ├── l2 │ │ ├── __init__.py │ │ ├── connectors │ │ │ ├── __init__.py │ │ │ ├── connector.py │ │ │ ├── eic │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── eic.py │ │ │ │ └── test_eic.py │ │ │ ├── hpkv.py │ │ │ ├── infinistore.py │ │ │ ├── mock.py │ │ │ ├── priskv │ │ │ │ ├── __init__.py │ │ │ │ └── priskv.py │ │ │ └── rocksdb.py │ │ ├── key_builders │ │ │ ├── __init__.py │ │ │ ├── hasher.py │ │ │ ├── hex_key_builder.py │ │ │ ├── key_builder.py │ │ │ ├── raw_key_builder.py │ │ │ ├── rolling_hash_key_builder.py │ │ │ └── simple_hash_key_builder.py │ │ ├── l2_cache.py │ │ ├── marshallers │ │ │ ├── __init__.py │ │ │ ├── marshaller.py │ │ │ ├── string_serializer.py │ │ │ ├── tensor_serializer.py │ │ │ └── zstd_compressor.py │ │ └── placement │ │ │ ├── __init__.py │ │ │ ├── placement.py │ │ │ └── simple_placement.py │ ├── memory │ │ ├── __init__.py │ │ ├── allocator.py │ │ ├── external_memory_region.py │ │ ├── memory_region.py │ │ └── ref_counted_obj.py │ ├── meta_service │ │ ├── __init__.py │ │ ├── meta_service.py │ │ └── redis_meta_service.py │ ├── metrics.py │ ├── profiling.py │ ├── spec.py │ ├── status.py │ ├── transport │ │ ├── __init__.py │ │ └── rdma.py │ ├── utils.py │ └── version.py │ ├── cmake │ └── utils.cmake │ ├── csrc │ ├── attention │ │ ├── attention_dtypes.h │ │ ├── attention_generic.cuh │ │ ├── dtype_bfloat16.cuh │ │ ├── dtype_float16.cuh │ │ ├── dtype_float32.cuh │ │ └── dtype_fp8.cuh │ ├── cache.h │ ├── cache_kernels.cu │ ├── core │ │ └── registration.h │ ├── quantization │ │ └── fp8 │ │ │ ├── amd │ │ │ └── quant_utils.cuh │ │ │ └── nvidia │ │ │ └── quant_utils.cuh │ └── torch_bindings.cpp │ ├── integration │ ├── sglang │ │ └── docker │ │ │ ├── Dockerfile │ │ │ └── README.md │ └── vllm │ │ ├── docker │ │ ├── Dockerfile │ │ └── README.md │ │ └── patches │ │ ├── vllm_v0.10.2-aibrix-kvcache.patch │ │ ├── vllm_v0.8.5-aibrix-kvcache.patch │ │ └── vllm_v0.9.1-aibrix-kvcache.patch │ ├── pyproject.toml │ ├── requirements │ ├── build.txt │ ├── core.txt │ ├── dev.txt │ ├── lint.txt │ └── test.txt │ ├── scripts │ ├── check_aibrix_header.py │ └── format.sh │ ├── setup.py │ └── tests │ ├── __init__.py │ ├── conftest.py │ ├── pytest.ini │ ├── test_cache_handle.py │ ├── test_cache_manager.py │ ├── test_cache_ops.py │ ├── test_common.py │ ├── test_eviction_policies.py │ ├── test_group_aware_cache_manager.py │ ├── test_key_builder.py │ ├── test_l1cache.py │ ├── test_l2cache.py │ ├── test_memory_region.py │ ├── test_placement.py │ └── test_tensor_pool_allocator.py ├── samples ├── adapter │ ├── adapter-api-key.yaml │ ├── adapter-multi-replica.yaml │ ├── adapter.yaml │ ├── base-api-key.yaml │ ├── base-without-runtime.yaml │ └── base.yaml ├── ai-gateway-integration │ ├── README.md │ ├── aigatewayroute.yaml │ ├── disaggregation │ │ ├── README.md │ │ ├── aigatewayroute.yaml │ │ ├── gateway.yaml │ │ ├── llm-d-inference-scheduler-epp.yaml │ │ ├── qwen2-7b-inferencepool.yaml │ │ └── vllm-sim-pd-stormservice.yaml │ ├── gateway.yaml │ ├── llama-7b-inferencepool.yaml │ ├── llama-7b.yaml │ ├── mistral-7b-inferencepool.yaml │ └── mistral-7b.yaml ├── autoscaling │ ├── apa-resource.yaml │ ├── apa.yaml │ ├── deploy.yaml │ ├── hpa.yaml │ ├── kpa.yaml │ ├── multimetrics-apa.yaml │ ├── optimizer-kpa.yaml │ ├── stormservice-pool.yaml │ └── stormservice-replica.yaml ├── deepseek-r1 │ ├── README.md │ ├── deepseek-r1-ai-runtime.yaml │ ├── deepseek-r1-autoscaling.yaml │ ├── deepseek-r1-huggingface.yaml │ ├── deepseek-r1-local-nvme.yaml │ ├── deepseek-r1-pvc.yaml │ ├── deepseek-r1-service.yaml │ ├── deepseek-r1-tcp.yaml │ └── static │ │ ├── AIBrix Engine Dashboard (vLLM)-1741078999667.json │ │ ├── deepseek-dashboard.png │ │ └── deepseek-deployment.png ├── disaggregation │ ├── sglang │ │ ├── README.md │ │ ├── pool.yaml │ │ ├── replica.yaml │ │ └── tp-1p1d.yaml │ └── vllm │ │ ├── 1p1d.yaml │ │ ├── README.md │ │ ├── disagg_proxy_server.py │ │ ├── pool.yaml │ │ ├── replica.yaml │ │ └── router.yaml ├── distributed │ ├── fleet-two-node.yaml │ └── fleet.yaml ├── heterogeneous │ ├── deepseek-coder-7b-l20-deployment.yaml │ ├── deepseek-coder-7b-l20-podautoscaler.yaml │ ├── deepseek-coder-7b-service.yaml │ ├── deepseek-coder-7b-v100-deployment.yaml │ ├── deepseek-coder-7b-v100-podautoscaler.yaml │ └── kustomization.yaml ├── kvcache │ ├── infinistore │ │ ├── kvcache.yaml │ │ ├── kvcache_customized.yaml │ │ └── vllm.yaml │ ├── l1cache │ │ └── vllm.yaml │ ├── profiling │ │ └── profiling_svc.yaml │ └── vineyard │ │ ├── deployment-tp.yaml │ │ ├── deployment.yaml │ │ ├── kvcache-tp.yaml │ │ └── kvcache.yaml ├── multimodality │ ├── vllm │ │ ├── README.md │ │ ├── dse-qwen2-2b.yaml │ │ ├── llava-7b.yaml │ │ ├── qwen-audio.yaml │ │ ├── qwen-vl.yaml │ │ └── send_file_base64.py │ └── xDiT │ │ ├── README.md │ │ ├── image-generation │ │ ├── aibrix_vke_kv_image_hunyuanDiT.yaml │ │ ├── aibrix_vke_kv_image_hunyuanDiT_parallel.yaml │ │ ├── aibrix_vke_kv_image_sd.yaml │ │ └── aibrix_vke_kv_image_sd_parallel.yaml │ │ ├── video-generation │ │ ├── aibrix_vke_staging_video_cogvideo_parallel.yaml │ │ └── aibrix_vke_staging_video_hunyuanvideo.yaml │ │ └── xDiT-integration │ │ └── xdit-52e74e88d2332281eefe68894af02f805a1d2b4f.patch ├── quickstart │ ├── model.yaml │ ├── pd-model.yaml │ └── vke │ │ ├── model.yaml │ │ └── pd-model.yaml └── volcano-engine │ ├── README.md │ ├── autoscaler.yaml │ ├── deepseek-8b-kv-cluster.yaml │ ├── deepseek-8b-kv-direct.yaml │ ├── deepseek-8b-kv-dram.yaml │ ├── deepseek-8b-naive.yaml │ ├── deepseek-r1.yaml │ ├── grafana.yaml │ ├── hpa-r1.yaml │ ├── kvcache.yaml │ └── prefix-cache-routing.ipynb ├── scripts └── port-forward.sh └── test ├── README.md ├── e2e ├── e2e_test.go ├── model_adapter_test.go ├── openai_api_compatibility_test.go ├── routing_strategy_test.go ├── util.go └── vtc_routing_test.go ├── integration ├── controller │ ├── podautoscaler_test.go │ ├── podset_test.go │ ├── roleset_test.go │ ├── stormservice_test.go │ └── suit_test.go ├── engine │ └── lora │ │ ├── README.md │ │ ├── create_test_loras.py │ │ ├── run_all_tests.py │ │ ├── test_api.py │ │ ├── test_batching_concurrency.py │ │ ├── test_config.py │ │ ├── test_lru_swap_pinning.py │ │ └── test_memory.py └── webhook │ ├── deployment_webhook_test.go │ ├── kvcache_webhook_test.go │ ├── modeladapter_test.go │ ├── podautoscaler_webhook_test.go │ ├── stormservice_webhook_test.go │ └── suit_test.go ├── kv-event-sync-e2e.rst ├── regression ├── v0.2.1 │ ├── README.md │ ├── aibrix_kvcache_0.6.1.yaml │ ├── aibrix_naive.yaml │ ├── benchmark_output_20250323.zip │ ├── client.yaml │ ├── k8s_stack.yaml │ ├── plot.py │ ├── ps_k8s_stack.yaml │ └── ps_stack.yaml ├── v0.3.0 │ ├── README.md │ ├── aibrix_kvcache_dram.yaml │ ├── aibrix_kvcache_external.yaml │ ├── aibrix_naive.yaml │ ├── aibrix_naive_prefix_cache.yaml │ ├── benchmark_output_20250519.zip │ ├── client.yaml │ ├── figure_ttft_generation_time.png │ ├── infinistore-hostnetwork.yaml │ ├── infinistore.yaml │ ├── k8s_stack.yaml │ ├── kvcache.yaml │ ├── lmcache_helm_naive.yaml │ ├── lmcache_helm_stack.yaml │ ├── plot.py │ └── ps_stack.yaml ├── v0.4.0 │ ├── Chart.yaml │ ├── README.md │ ├── benchmark-client.yaml │ ├── configs │ │ ├── sglang-disagg-base.yaml │ │ ├── sglang-non-disagg-base.yaml │ │ ├── vllm-disagg-base.yaml │ │ └── vllm-non-disagg-base.yaml │ ├── dynamo │ │ ├── disagg.yaml │ │ └── disagg_router.yaml │ ├── multi-engine │ │ ├── sglang-llama-8b.yaml │ │ └── vllm-llama-8b.yaml │ ├── templates │ │ ├── _helpers.tpl │ │ ├── sglang-disaggregated.yaml │ │ ├── sglang-non-disaggregated.yaml │ │ ├── vllm-disaggregated.yaml │ │ └── vllm-non-disaggregated.yaml │ └── values.yaml └── v0.5.0 │ ├── sglang-xpyd-rdma.yaml │ └── vllm-xpyd-rdma.yaml ├── run-e2e-tests.sh └── utils ├── utils.go ├── validation ├── hpa.go ├── pod.go ├── podautoscaler.go ├── podset.go ├── roleset.go └── stormservice.go └── wrapper ├── deployment.go ├── kvcache.go ├── modeladapter.go ├── podautoscaler.go ├── podset.go ├── roleset.go └── stormservice.go /.github/.testcoverage.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/.testcoverage.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/100_feature_request.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/ISSUE_TEMPLATE/100_feature_request.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/200_bug_report.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/ISSUE_TEMPLATE/200_bug_report.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/300_RFC.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/ISSUE_TEMPLATE/300_RFC.yml -------------------------------------------------------------------------------- /.github/PULL_REQUEST_TEMPLATE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/PULL_REQUEST_TEMPLATE.md -------------------------------------------------------------------------------- /.github/workflows/chart-ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/chart-ci.yml -------------------------------------------------------------------------------- /.github/workflows/docker-build-images.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/docker-build-images.yml -------------------------------------------------------------------------------- /.github/workflows/docker-push-images.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/docker-push-images.yml -------------------------------------------------------------------------------- /.github/workflows/installation-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/installation-tests.yml -------------------------------------------------------------------------------- /.github/workflows/lint-and-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/lint-and-tests.yml -------------------------------------------------------------------------------- /.github/workflows/python-aibrix-kvcache-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/python-aibrix-kvcache-tests.yml -------------------------------------------------------------------------------- /.github/workflows/python-aibrix-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/python-aibrix-tests.yml -------------------------------------------------------------------------------- /.github/workflows/release-build.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.github/workflows/release-build.yaml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.gitignore -------------------------------------------------------------------------------- /.golangci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.golangci.yml -------------------------------------------------------------------------------- /.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/.readthedocs.yaml -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/Makefile -------------------------------------------------------------------------------- /PROJECT: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/PROJECT -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/README.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/SECURITY.md -------------------------------------------------------------------------------- /api/autoscaling/v1alpha1/groupversion_info.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/autoscaling/v1alpha1/groupversion_info.go -------------------------------------------------------------------------------- /api/autoscaling/v1alpha1/podautoscaler_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/autoscaling/v1alpha1/podautoscaler_types.go -------------------------------------------------------------------------------- /api/autoscaling/v1alpha1/zz_generated.deepcopy.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/autoscaling/v1alpha1/zz_generated.deepcopy.go -------------------------------------------------------------------------------- /api/model/v1alpha1/groupversion_info.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/model/v1alpha1/groupversion_info.go -------------------------------------------------------------------------------- /api/model/v1alpha1/modeladapter_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/model/v1alpha1/modeladapter_types.go -------------------------------------------------------------------------------- /api/model/v1alpha1/zz_generated.deepcopy.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/model/v1alpha1/zz_generated.deepcopy.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/condition.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/condition.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/groupversion_info.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/groupversion_info.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/kvcache_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/kvcache_types.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/podset_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/podset_types.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/raycluster_type.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/raycluster_type.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/roleset_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/roleset_types.go -------------------------------------------------------------------------------- /api/orchestration/v1alpha1/stormservice_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/api/orchestration/v1alpha1/stormservice_types.go -------------------------------------------------------------------------------- /benchmarks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/README.md -------------------------------------------------------------------------------- /benchmarks/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/benchmark.py -------------------------------------------------------------------------------- /benchmarks/client/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/client/README.md -------------------------------------------------------------------------------- /benchmarks/client/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/client/analyze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/client/analyze.py -------------------------------------------------------------------------------- /benchmarks/client/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/client/client.py -------------------------------------------------------------------------------- /benchmarks/client/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/client/utils.py -------------------------------------------------------------------------------- /benchmarks/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/config.yaml -------------------------------------------------------------------------------- /benchmarks/generator/.gitignore: -------------------------------------------------------------------------------- 1 | output 2 | plot 3 | -------------------------------------------------------------------------------- /benchmarks/generator/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/generator/dataset_generator/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/generator/dataset_generator/README.md -------------------------------------------------------------------------------- /benchmarks/generator/dataset_generator/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/generator/dataset_generator/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/generator/dataset_generator/util.py -------------------------------------------------------------------------------- /benchmarks/generator/dataset_generator/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/generator/dataset_generator/utility.py -------------------------------------------------------------------------------- /benchmarks/generator/workload_generator/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/generator/workload_generator/README.md -------------------------------------------------------------------------------- /benchmarks/generator/workload_generator/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/generator/workload_generator/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/generator/workload_generator/utils.py -------------------------------------------------------------------------------- /benchmarks/image/aibrix-benchmark-client.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/image/aibrix-benchmark-client.png -------------------------------------------------------------------------------- /benchmarks/image/aibrix-benchmark-component.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/image/aibrix-benchmark-component.png -------------------------------------------------------------------------------- /benchmarks/image/aibrix-benchmark-dataset.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/image/aibrix-benchmark-dataset.png -------------------------------------------------------------------------------- /benchmarks/image/aibrix-benchmark-workload.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/image/aibrix-benchmark-workload.png -------------------------------------------------------------------------------- /benchmarks/plot/aibrix0.1-downloader.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/plot/aibrix0.1-downloader.ipynb -------------------------------------------------------------------------------- /benchmarks/plot/aibrix0.1-lora.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/plot/aibrix0.1-lora.ipynb -------------------------------------------------------------------------------- /benchmarks/plot/aibrix0.1-routing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/plot/aibrix0.1-routing.ipynb -------------------------------------------------------------------------------- /benchmarks/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/requirements.txt -------------------------------------------------------------------------------- /benchmarks/scenarios/autoscaling/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/autoscaling/README.md -------------------------------------------------------------------------------- /benchmarks/scenarios/autoscaling/overnight_run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/autoscaling/overnight_run.sh -------------------------------------------------------------------------------- /benchmarks/scenarios/autoscaling/plot_per_pod.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/autoscaling/plot_per_pod.py -------------------------------------------------------------------------------- /benchmarks/scenarios/autoscaling/run-test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/autoscaling/run-test.sh -------------------------------------------------------------------------------- /benchmarks/scenarios/gateway/7b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/gateway/7b.yaml -------------------------------------------------------------------------------- /benchmarks/scenarios/gateway/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/gateway/README.md -------------------------------------------------------------------------------- /benchmarks/scenarios/gateway/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/gateway/benchmark.py -------------------------------------------------------------------------------- /benchmarks/scenarios/gateway/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/gateway/client.py -------------------------------------------------------------------------------- /benchmarks/scenarios/kvcache/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/kvcache/README.md -------------------------------------------------------------------------------- /benchmarks/scenarios/lora/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/lora/README.md -------------------------------------------------------------------------------- /benchmarks/scenarios/lora/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/lora/benchmark.py -------------------------------------------------------------------------------- /benchmarks/scenarios/utils/check_k8s_is_ready.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/utils/check_k8s_is_ready.py -------------------------------------------------------------------------------- /benchmarks/scenarios/utils/count_num_pods.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/utils/count_num_pods.py -------------------------------------------------------------------------------- /benchmarks/scenarios/utils/set_num_replicas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/benchmarks/scenarios/utils/set_num_replicas.py -------------------------------------------------------------------------------- /cmd/controllers/main.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/cmd/controllers/main.go -------------------------------------------------------------------------------- /cmd/kvcache-watcher/main.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/cmd/kvcache-watcher/main.go -------------------------------------------------------------------------------- /cmd/plugins/main.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/cmd/plugins/main.go -------------------------------------------------------------------------------- /config/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/.gitignore -------------------------------------------------------------------------------- /config/crd/autoscaling/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/crd/autoscaling/kustomization.yaml -------------------------------------------------------------------------------- /config/crd/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/crd/kustomization.yaml -------------------------------------------------------------------------------- /config/crd/kustomizeconfig.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/crd/kustomizeconfig.yaml -------------------------------------------------------------------------------- /config/crd/model/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/crd/model/kustomization.yaml -------------------------------------------------------------------------------- /config/crd/orchestration/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/crd/orchestration/kustomization.yaml -------------------------------------------------------------------------------- /config/default/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/default/kustomization.yaml -------------------------------------------------------------------------------- /config/default/manager_webhook_patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/default/manager_webhook_patch.yaml -------------------------------------------------------------------------------- /config/default/webhookcainjection_patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/default/webhookcainjection_patch.yaml -------------------------------------------------------------------------------- /config/dependency/kuberay-operator/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/dependency/kuberay-operator/README.md -------------------------------------------------------------------------------- /config/dependency/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/dependency/kustomization.yaml -------------------------------------------------------------------------------- /config/gateway/gateway-plugin/gateway-plugin.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gateway/gateway-plugin/gateway-plugin.yaml -------------------------------------------------------------------------------- /config/gateway/gateway-plugin/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gateway/gateway-plugin/kustomization.yaml -------------------------------------------------------------------------------- /config/gateway/gateway.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gateway/gateway.yaml -------------------------------------------------------------------------------- /config/gateway/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gateway/kustomization.yaml -------------------------------------------------------------------------------- /config/gpu-optimizer/deployment.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gpu-optimizer/deployment.yaml -------------------------------------------------------------------------------- /config/gpu-optimizer/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gpu-optimizer/kustomization.yaml -------------------------------------------------------------------------------- /config/gpu-optimizer/rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gpu-optimizer/rbac.yaml -------------------------------------------------------------------------------- /config/gpu-optimizer/service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/gpu-optimizer/service.yaml -------------------------------------------------------------------------------- /config/internalcert/kustomization.yaml: -------------------------------------------------------------------------------- 1 | resources: 2 | - secret.yaml 3 | -------------------------------------------------------------------------------- /config/internalcert/secret.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/internalcert/secret.yaml -------------------------------------------------------------------------------- /config/job/k8s_job_rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/job/k8s_job_rbac.yaml -------------------------------------------------------------------------------- /config/job/kustomization.yaml: -------------------------------------------------------------------------------- 1 | kind: Kustomization 2 | 3 | resources: 4 | - k8s_job_rbac.yaml -------------------------------------------------------------------------------- /config/manager/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/manager/kustomization.yaml -------------------------------------------------------------------------------- /config/manager/manager.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/manager/manager.yaml -------------------------------------------------------------------------------- /config/metadata/job_template_patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/metadata/job_template_patch.yaml -------------------------------------------------------------------------------- /config/metadata/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/metadata/kustomization.yaml -------------------------------------------------------------------------------- /config/metadata/metadata.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/metadata/metadata.yaml -------------------------------------------------------------------------------- /config/metadata/redis.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/metadata/redis.yaml -------------------------------------------------------------------------------- /config/metadata/s3-env-patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/metadata/s3-env-patch.yaml -------------------------------------------------------------------------------- /config/metadata/tos-env-patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/metadata/tos-env-patch.yaml -------------------------------------------------------------------------------- /config/namespace/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/namespace/kustomization.yaml -------------------------------------------------------------------------------- /config/namespace/namespace.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/namespace/namespace.yaml -------------------------------------------------------------------------------- /config/overlays/dev/manager/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/dev/manager/kustomization.yaml -------------------------------------------------------------------------------- /config/overlays/release/envoy_proxy_patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/release/envoy_proxy_patch.yaml -------------------------------------------------------------------------------- /config/overlays/release/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/release/kustomization.yaml -------------------------------------------------------------------------------- /config/overlays/release/pdb.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/release/pdb.yaml -------------------------------------------------------------------------------- /config/overlays/vke-ipv6/envoy_proxy_patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/vke-ipv6/envoy_proxy_patch.yaml -------------------------------------------------------------------------------- /config/overlays/vke-ipv6/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/vke-ipv6/kustomization.yaml -------------------------------------------------------------------------------- /config/overlays/vke/default/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/vke/default/kustomization.yaml -------------------------------------------------------------------------------- /config/overlays/vke/dependency/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/overlays/vke/dependency/kustomization.yaml -------------------------------------------------------------------------------- /config/prometheus/kustomization.yaml: -------------------------------------------------------------------------------- 1 | resources: 2 | - monitor.yaml 3 | -------------------------------------------------------------------------------- /config/prometheus/monitor.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/prometheus/monitor.yaml -------------------------------------------------------------------------------- /config/rbac/autoscaling/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/autoscaling/kustomization.yaml -------------------------------------------------------------------------------- /config/rbac/controller-manager/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/controller-manager/kustomization.yaml -------------------------------------------------------------------------------- /config/rbac/controller-manager/role.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/controller-manager/role.yaml -------------------------------------------------------------------------------- /config/rbac/controller-manager/role_binding.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/controller-manager/role_binding.yaml -------------------------------------------------------------------------------- /config/rbac/gateway/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/gateway/kustomization.yaml -------------------------------------------------------------------------------- /config/rbac/gateway/role_binding_gateway.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/gateway/role_binding_gateway.yaml -------------------------------------------------------------------------------- /config/rbac/gateway/role_gateway.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/gateway/role_gateway.yaml -------------------------------------------------------------------------------- /config/rbac/gateway/service_account_gateway.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/gateway/service_account_gateway.yaml -------------------------------------------------------------------------------- /config/rbac/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/kustomization.yaml -------------------------------------------------------------------------------- /config/rbac/model/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/model/kustomization.yaml -------------------------------------------------------------------------------- /config/rbac/orchestration/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/rbac/orchestration/kustomization.yaml -------------------------------------------------------------------------------- /config/samples/autoscaling_v1alpha1_kpa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/samples/autoscaling_v1alpha1_kpa.yaml -------------------------------------------------------------------------------- /config/samples/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/samples/kustomization.yaml -------------------------------------------------------------------------------- /config/samples/model_v1alpha1_modeladapter.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/samples/model_v1alpha1_modeladapter.yaml -------------------------------------------------------------------------------- /config/standalone/kv-cache-controller/patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/standalone/kv-cache-controller/patch.yaml -------------------------------------------------------------------------------- /config/test/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/test/README.md -------------------------------------------------------------------------------- /config/test/gateway/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/test/gateway/kustomization.yaml -------------------------------------------------------------------------------- /config/test/gateway/vtc-test-env-patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/test/gateway/vtc-test-env-patch.yaml -------------------------------------------------------------------------------- /config/test/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/test/kustomization.yaml -------------------------------------------------------------------------------- /config/webhook/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/webhook/kustomization.yaml -------------------------------------------------------------------------------- /config/webhook/kustomizeconfig.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/webhook/kustomizeconfig.yaml -------------------------------------------------------------------------------- /config/webhook/manifests.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/webhook/manifests.yaml -------------------------------------------------------------------------------- /config/webhook/service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/config/webhook/service.yaml -------------------------------------------------------------------------------- /deployment/terraform/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/.gitignore -------------------------------------------------------------------------------- /deployment/terraform/gcp/.terraform-docs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/.terraform-docs.yml -------------------------------------------------------------------------------- /deployment/terraform/gcp/.terraform.lock.hcl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/.terraform.lock.hcl -------------------------------------------------------------------------------- /deployment/terraform/gcp/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/README.md -------------------------------------------------------------------------------- /deployment/terraform/gcp/cluster/data.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/cluster/data.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/cluster/main.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/cluster/main.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/cluster/outputs.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/cluster/outputs.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/cluster/terraform.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/cluster/terraform.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/cluster/variables.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/cluster/variables.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/data.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/data.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/docs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/docs.md -------------------------------------------------------------------------------- /deployment/terraform/gcp/locals.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/locals.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/main.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/main.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/outputs.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/outputs.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/providers.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/providers.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/terraform.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/terraform.tf -------------------------------------------------------------------------------- /deployment/terraform/gcp/terraform.tfvars.example: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/terraform.tfvars.example -------------------------------------------------------------------------------- /deployment/terraform/gcp/variables.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/gcp/variables.tf -------------------------------------------------------------------------------- /deployment/terraform/go.mod: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/go.mod -------------------------------------------------------------------------------- /deployment/terraform/go.sum: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/go.sum -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/README.md -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/data.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/data.tf -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/locals.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/locals.tf -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/main.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/main.tf -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/outputs.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/outputs.tf -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/terraform.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/terraform.tf -------------------------------------------------------------------------------- /deployment/terraform/kubernetes/variables.tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/kubernetes/variables.tf -------------------------------------------------------------------------------- /deployment/terraform/tests/gcp_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/deployment/terraform/tests/gcp_test.go -------------------------------------------------------------------------------- /development/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/README.md -------------------------------------------------------------------------------- /development/app/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/Dockerfile -------------------------------------------------------------------------------- /development/app/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/Makefile -------------------------------------------------------------------------------- /development/app/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/README.md -------------------------------------------------------------------------------- /development/app/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/app.py -------------------------------------------------------------------------------- /development/app/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/config.json -------------------------------------------------------------------------------- /development/app/config/mock/api-key-patch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/config/mock/api-key-patch.yaml -------------------------------------------------------------------------------- /development/app/config/mock/components.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/config/mock/components.yaml -------------------------------------------------------------------------------- /development/app/config/mock/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/config/mock/kustomization.yaml -------------------------------------------------------------------------------- /development/app/config/templates/deployment/kustomization.yaml: -------------------------------------------------------------------------------- 1 | resources: 2 | - deployment.yaml 3 | -------------------------------------------------------------------------------- /development/app/config/templates/podautoscaler/kustomization.yaml: -------------------------------------------------------------------------------- 1 | resources: 2 | - podautoscaler_kpa.yaml 3 | -------------------------------------------------------------------------------- /development/app/config/vke/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/config/vke/kustomization.yaml -------------------------------------------------------------------------------- /development/app/entrypoint.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/entrypoint.sh -------------------------------------------------------------------------------- /development/app/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/requirements.txt -------------------------------------------------------------------------------- /development/app/simulator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/simulator.py -------------------------------------------------------------------------------- /development/app/test_app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/test_app.py -------------------------------------------------------------------------------- /development/app/zscaler_root_ca.crt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/app/zscaler_root_ca.crt -------------------------------------------------------------------------------- /development/tutorials/batch/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/batch/README.md -------------------------------------------------------------------------------- /development/tutorials/distributed/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/distributed/README.md -------------------------------------------------------------------------------- /development/tutorials/distributed/fleet-mock.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/distributed/fleet-mock.yaml -------------------------------------------------------------------------------- /development/tutorials/distributed/fleet.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/distributed/fleet.yaml -------------------------------------------------------------------------------- /development/tutorials/distributed/raycluster.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/distributed/raycluster.yaml -------------------------------------------------------------------------------- /development/tutorials/distributed/rayjob.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/distributed/rayjob.yaml -------------------------------------------------------------------------------- /development/tutorials/kvcache/kvcache.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/kvcache/kvcache.yaml -------------------------------------------------------------------------------- /development/tutorials/lora/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/lora/README.md -------------------------------------------------------------------------------- /development/tutorials/lora/deployment.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/lora/deployment.yaml -------------------------------------------------------------------------------- /development/tutorials/lora/model_adapter.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/lora/model_adapter.yaml -------------------------------------------------------------------------------- /development/tutorials/podautoscaler/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/podautoscaler/README.md -------------------------------------------------------------------------------- /development/tutorials/podautoscaler/hpa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/podautoscaler/hpa.yaml -------------------------------------------------------------------------------- /development/tutorials/podautoscaler/pa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/podautoscaler/pa.yaml -------------------------------------------------------------------------------- /development/tutorials/runtime/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/tutorials/runtime/README.md -------------------------------------------------------------------------------- /development/vllm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/vllm/README.md -------------------------------------------------------------------------------- /development/vllm/kind-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/vllm/kind-config.yaml -------------------------------------------------------------------------------- /development/vllm/linux/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/vllm/linux/kustomization.yaml -------------------------------------------------------------------------------- /development/vllm/macos/components.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/vllm/macos/components.yaml -------------------------------------------------------------------------------- /development/vllm/macos/deployment.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/vllm/macos/deployment.yaml -------------------------------------------------------------------------------- /development/vllm/macos/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/development/vllm/macos/kustomization.yaml -------------------------------------------------------------------------------- /dist/chart/.helmignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/.helmignore -------------------------------------------------------------------------------- /dist/chart/Chart.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/Chart.yaml -------------------------------------------------------------------------------- /dist/chart/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/README.md -------------------------------------------------------------------------------- /dist/chart/stable.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/stable.yaml -------------------------------------------------------------------------------- /dist/chart/templates/_helpers.tpl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/_helpers.tpl -------------------------------------------------------------------------------- /dist/chart/templates/controller-manager/rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/controller-manager/rbac.yaml -------------------------------------------------------------------------------- /dist/chart/templates/gateway-plugin/rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/gateway-plugin/rbac.yaml -------------------------------------------------------------------------------- /dist/chart/templates/gateway-plugin/service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/gateway-plugin/service.yaml -------------------------------------------------------------------------------- /dist/chart/templates/gpu-optimizer/rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/gpu-optimizer/rbac.yaml -------------------------------------------------------------------------------- /dist/chart/templates/gpu-optimizer/service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/gpu-optimizer/service.yaml -------------------------------------------------------------------------------- /dist/chart/templates/metadata-service/rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/metadata-service/rbac.yaml -------------------------------------------------------------------------------- /dist/chart/templates/metadata-service/redis.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/metadata-service/redis.yaml -------------------------------------------------------------------------------- /dist/chart/templates/prometheus/monitor.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/prometheus/monitor.yaml -------------------------------------------------------------------------------- /dist/chart/templates/webhook/secret.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/webhook/secret.yaml -------------------------------------------------------------------------------- /dist/chart/templates/webhook/service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/webhook/service.yaml -------------------------------------------------------------------------------- /dist/chart/templates/webhook/webhooks.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/templates/webhook/webhooks.yaml -------------------------------------------------------------------------------- /dist/chart/values.schema.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/values.schema.json -------------------------------------------------------------------------------- /dist/chart/values.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/values.yaml -------------------------------------------------------------------------------- /dist/chart/vke.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/dist/chart/vke.yaml -------------------------------------------------------------------------------- /docs/.gitattributes: -------------------------------------------------------------------------------- 1 | *.ipynb linguist-vendored 2 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/README.md -------------------------------------------------------------------------------- /docs/kv-event-sync-readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/kv-event-sync-readme.md -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/paper/AIBrix_White_Paper_0219_2025.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/paper/AIBrix_White_Paper_0219_2025.pdf -------------------------------------------------------------------------------- /docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/requirements-docs.txt -------------------------------------------------------------------------------- /docs/source/assets/images/draft-release.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/assets/images/draft-release.png -------------------------------------------------------------------------------- /docs/source/assets/images/gateway-design.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/assets/images/gateway-design.png -------------------------------------------------------------------------------- /docs/source/assets/images/model-error.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/assets/images/model-error.png -------------------------------------------------------------------------------- /docs/source/assets/logos/aibrix-logo.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/assets/logos/aibrix-logo.jpeg -------------------------------------------------------------------------------- /docs/source/community/community.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/community/community.rst -------------------------------------------------------------------------------- /docs/source/community/contribution.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/community/contribution.rst -------------------------------------------------------------------------------- /docs/source/community/research.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/community/research.rst -------------------------------------------------------------------------------- /docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/conf.py -------------------------------------------------------------------------------- /docs/source/designs/aibrix-autoscaler.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/designs/aibrix-autoscaler.rst -------------------------------------------------------------------------------- /docs/source/designs/aibrix-engine-runtime.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/designs/aibrix-engine-runtime.rst -------------------------------------------------------------------------------- /docs/source/designs/aibrix-router.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/designs/aibrix-router.rst -------------------------------------------------------------------------------- /docs/source/designs/aibrix-stormservice.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/designs/aibrix-stormservice.rst -------------------------------------------------------------------------------- /docs/source/designs/architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/designs/architecture.rst -------------------------------------------------------------------------------- /docs/source/development/development.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/development/development.rst -------------------------------------------------------------------------------- /docs/source/development/release.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/development/release.rst -------------------------------------------------------------------------------- /docs/source/features/autoscaling/autoscaling.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/autoscaling/autoscaling.rst -------------------------------------------------------------------------------- /docs/source/features/batch-api.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/batch-api.rst -------------------------------------------------------------------------------- /docs/source/features/benchmark-and-generator.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/benchmark-and-generator.rst -------------------------------------------------------------------------------- /docs/source/features/gateway-plugins.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/gateway-plugins.rst -------------------------------------------------------------------------------- /docs/source/features/heterogeneous-gpu.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/heterogeneous-gpu.rst -------------------------------------------------------------------------------- /docs/source/features/kv-event-sync.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/kv-event-sync.rst -------------------------------------------------------------------------------- /docs/source/features/kvcache-offloading.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/kvcache-offloading.rst -------------------------------------------------------------------------------- /docs/source/features/lora-dynamic-loading.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/lora-dynamic-loading.rst -------------------------------------------------------------------------------- /docs/source/features/multi-engine.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/multi-engine.rst -------------------------------------------------------------------------------- /docs/source/features/multi-node-inference.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/multi-node-inference.rst -------------------------------------------------------------------------------- /docs/source/features/runtime.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/features/runtime.rst -------------------------------------------------------------------------------- /docs/source/getting_started/container-images.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/getting_started/container-images.rst -------------------------------------------------------------------------------- /docs/source/getting_started/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/getting_started/faq.rst -------------------------------------------------------------------------------- /docs/source/getting_started/installation/aws.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/getting_started/installation/aws.rst -------------------------------------------------------------------------------- /docs/source/getting_started/installation/gcp.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/getting_started/installation/gcp.rst -------------------------------------------------------------------------------- /docs/source/getting_started/installation/vke.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/getting_started/installation/vke.rst -------------------------------------------------------------------------------- /docs/source/getting_started/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/getting_started/quickstart.rst -------------------------------------------------------------------------------- /docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/index.rst -------------------------------------------------------------------------------- /docs/source/production/observability.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/docs/source/production/observability.rst -------------------------------------------------------------------------------- /go.mod: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/go.mod -------------------------------------------------------------------------------- /go.sum: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/go.sum -------------------------------------------------------------------------------- /hack/boilerplate.go.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/boilerplate.go.txt -------------------------------------------------------------------------------- /hack/ci/kind-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/ci/kind-config.yaml -------------------------------------------------------------------------------- /hack/enable-kv-events.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/enable-kv-events.sh -------------------------------------------------------------------------------- /hack/lambda-cloud/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/lambda-cloud/README.md -------------------------------------------------------------------------------- /hack/lambda-cloud/install.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/lambda-cloud/install.sh -------------------------------------------------------------------------------- /hack/lambda-cloud/nvkind-cluster.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/lambda-cloud/nvkind-cluster.yaml -------------------------------------------------------------------------------- /hack/lambda-cloud/setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/lambda-cloud/setup.sh -------------------------------------------------------------------------------- /hack/lambda-cloud/verify.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/lambda-cloud/verify.sh -------------------------------------------------------------------------------- /hack/rdma/detect-gid-in-container.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/rdma/detect-gid-in-container.sh -------------------------------------------------------------------------------- /hack/rdma/search-gid.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/rdma/search-gid.sh -------------------------------------------------------------------------------- /hack/release/sync-dependency-images.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/release/sync-dependency-images.sh -------------------------------------------------------------------------------- /hack/release/sync-images.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/release/sync-images.sh -------------------------------------------------------------------------------- /hack/tools.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/tools.go -------------------------------------------------------------------------------- /hack/update-codegen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/update-codegen.sh -------------------------------------------------------------------------------- /hack/verify-codegen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/verify-codegen.sh -------------------------------------------------------------------------------- /hack/verify-crd-sync.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/hack/verify-crd-sync.sh -------------------------------------------------------------------------------- /observability/monitor/envoy_metrics_service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/observability/monitor/envoy_metrics_service.yaml -------------------------------------------------------------------------------- /observability/monitor/service_monitor_vllm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/observability/monitor/service_monitor_vllm.yaml -------------------------------------------------------------------------------- /pkg/cache/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/README.md -------------------------------------------------------------------------------- /pkg/cache/build_verification_default_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/build_verification_default_test.go -------------------------------------------------------------------------------- /pkg/cache/build_verification_zmq_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/build_verification_zmq_test.go -------------------------------------------------------------------------------- /pkg/cache/cache_api.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_api.go -------------------------------------------------------------------------------- /pkg/cache/cache_impl.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_impl.go -------------------------------------------------------------------------------- /pkg/cache/cache_init.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_init.go -------------------------------------------------------------------------------- /pkg/cache/cache_init_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_init_test.go -------------------------------------------------------------------------------- /pkg/cache/cache_log.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_log.go -------------------------------------------------------------------------------- /pkg/cache/cache_metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_metrics.go -------------------------------------------------------------------------------- /pkg/cache/cache_profile.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_profile.go -------------------------------------------------------------------------------- /pkg/cache/cache_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_test.go -------------------------------------------------------------------------------- /pkg/cache/cache_trace.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/cache_trace.go -------------------------------------------------------------------------------- /pkg/cache/errors.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/errors.go -------------------------------------------------------------------------------- /pkg/cache/informers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/informers.go -------------------------------------------------------------------------------- /pkg/cache/kv_event_manager.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kv_event_manager.go -------------------------------------------------------------------------------- /pkg/cache/kv_event_manager_validation_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kv_event_manager_validation_test.go -------------------------------------------------------------------------------- /pkg/cache/kv_event_manager_zmq.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kv_event_manager_zmq.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/README.md -------------------------------------------------------------------------------- /pkg/cache/kvcache/endpoint.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/endpoint.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/endpoint_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/endpoint_test.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/event_types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/event_types.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/metrics.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/metrics_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/metrics_test.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/msgpack_decoder.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/msgpack_decoder.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/msgpack_decoder_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/msgpack_decoder_test.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/msgpack_encoder.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/msgpack_encoder.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/types.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/zmq_client.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/zmq_client.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/zmq_client_stub.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/zmq_client_stub.go -------------------------------------------------------------------------------- /pkg/cache/kvcache/zmq_client_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/kvcache/zmq_client_test.go -------------------------------------------------------------------------------- /pkg/cache/load_provider.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/load_provider.go -------------------------------------------------------------------------------- /pkg/cache/model.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/model.go -------------------------------------------------------------------------------- /pkg/cache/model_gpu_profile.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/model_gpu_profile.go -------------------------------------------------------------------------------- /pkg/cache/model_gpu_profile_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/model_gpu_profile_test.go -------------------------------------------------------------------------------- /pkg/cache/output_predictor.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/output_predictor.go -------------------------------------------------------------------------------- /pkg/cache/output_predictor_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/output_predictor_test.go -------------------------------------------------------------------------------- /pkg/cache/pending_load_provider.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/pending_load_provider.go -------------------------------------------------------------------------------- /pkg/cache/pod.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/pod.go -------------------------------------------------------------------------------- /pkg/cache/store_providers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/store_providers.go -------------------------------------------------------------------------------- /pkg/cache/store_providers_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/store_providers_test.go -------------------------------------------------------------------------------- /pkg/cache/test_helpers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/test_helpers.go -------------------------------------------------------------------------------- /pkg/cache/trace.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/trace.go -------------------------------------------------------------------------------- /pkg/cache/trace_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/trace_test.go -------------------------------------------------------------------------------- /pkg/cache/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cache/utils.go -------------------------------------------------------------------------------- /pkg/cert/cert.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/cert/cert.go -------------------------------------------------------------------------------- /pkg/client/applyconfiguration/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/applyconfiguration/utils.go -------------------------------------------------------------------------------- /pkg/client/clientset/versioned/clientset.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/clientset/versioned/clientset.go -------------------------------------------------------------------------------- /pkg/client/clientset/versioned/fake/doc.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/clientset/versioned/fake/doc.go -------------------------------------------------------------------------------- /pkg/client/clientset/versioned/fake/register.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/clientset/versioned/fake/register.go -------------------------------------------------------------------------------- /pkg/client/clientset/versioned/scheme/doc.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/clientset/versioned/scheme/doc.go -------------------------------------------------------------------------------- /pkg/client/clientset/versioned/scheme/register.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/clientset/versioned/scheme/register.go -------------------------------------------------------------------------------- /pkg/client/informers/externalversions/factory.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/informers/externalversions/factory.go -------------------------------------------------------------------------------- /pkg/client/informers/externalversions/generic.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/informers/externalversions/generic.go -------------------------------------------------------------------------------- /pkg/client/listers/model/v1alpha1/modeladapter.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/client/listers/model/v1alpha1/modeladapter.go -------------------------------------------------------------------------------- /pkg/config/config.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/config/config.go -------------------------------------------------------------------------------- /pkg/constants/kv_event_sync.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/constants/kv_event_sync.go -------------------------------------------------------------------------------- /pkg/constants/kvcache.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/constants/kvcache.go -------------------------------------------------------------------------------- /pkg/constants/metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/constants/metrics.go -------------------------------------------------------------------------------- /pkg/constants/model.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/constants/model.go -------------------------------------------------------------------------------- /pkg/controller/constants/stormservice.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/constants/stormservice.go -------------------------------------------------------------------------------- /pkg/controller/controller.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/controller.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/common.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/common.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/common_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/common_test.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/distributed.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/distributed.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/hpkv.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/hpkv.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/hpkv_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/hpkv_test.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/infinistore.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/infinistore.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/reconciler.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/reconciler.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/backends/vineyard.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/backends/vineyard.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/kvcache_controller.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/kvcache_controller.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/kvcache_controller_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/kvcache_controller_test.go -------------------------------------------------------------------------------- /pkg/controller/kvcache/suite_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/kvcache/suite_test.go -------------------------------------------------------------------------------- /pkg/controller/modeladapter/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/README.md -------------------------------------------------------------------------------- /pkg/controller/modeladapter/resources.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/resources.go -------------------------------------------------------------------------------- /pkg/controller/modeladapter/resources_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/resources_test.go -------------------------------------------------------------------------------- /pkg/controller/modeladapter/scheduling/random.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/scheduling/random.go -------------------------------------------------------------------------------- /pkg/controller/modeladapter/suite_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/suite_test.go -------------------------------------------------------------------------------- /pkg/controller/modeladapter/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/utils.go -------------------------------------------------------------------------------- /pkg/controller/modeladapter/utils_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/modeladapter/utils_test.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/algorithm/apa.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/algorithm/apa.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/algorithm/hpa.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/algorithm/hpa.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/algorithm/kpa.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/algorithm/kpa.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/autoscaler.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/autoscaler.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/autoscaler_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/autoscaler_test.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/context/context.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/context/context.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/hpa_resources.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/hpa_resources.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/metrics/client.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/metrics/client.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/metrics/collector.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/metrics/collector.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/metrics/fetcher.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/metrics/fetcher.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/metrics/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/metrics/utils.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/monitor/metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/monitor/metrics.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/monitor/monitor.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/monitor/monitor.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/types/annotations.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/types/annotations.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/types/core.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/types/core.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/types/metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/types/metrics.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/utils.go -------------------------------------------------------------------------------- /pkg/controller/podautoscaler/workload_scale.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podautoscaler/workload_scale.go -------------------------------------------------------------------------------- /pkg/controller/podset/podset_controller.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/podset/podset_controller.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/progress.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/progress.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/recreate.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/recreate.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/rollback.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/rollback.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/rolling.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/rolling.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/suite_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/suite_test.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/sync.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/sync.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterfleet/util/fleet.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterfleet/util/fleet.go -------------------------------------------------------------------------------- /pkg/controller/rayclusterreplicaset/suite_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/rayclusterreplicaset/suite_test.go -------------------------------------------------------------------------------- /pkg/controller/roleset/podset_rollsyncer.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/podset_rollsyncer.go -------------------------------------------------------------------------------- /pkg/controller/roleset/roleset_controller.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/roleset_controller.go -------------------------------------------------------------------------------- /pkg/controller/roleset/roleset_controller_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/roleset_controller_test.go -------------------------------------------------------------------------------- /pkg/controller/roleset/rolesyncer.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/rolesyncer.go -------------------------------------------------------------------------------- /pkg/controller/roleset/rolesyncer_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/rolesyncer_test.go -------------------------------------------------------------------------------- /pkg/controller/roleset/rolling.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/rolling.go -------------------------------------------------------------------------------- /pkg/controller/roleset/suite_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/suite_test.go -------------------------------------------------------------------------------- /pkg/controller/roleset/sync.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/sync.go -------------------------------------------------------------------------------- /pkg/controller/roleset/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/utils.go -------------------------------------------------------------------------------- /pkg/controller/roleset/utils_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/roleset/utils_test.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/revision.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/revision.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/revision_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/revision_test.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/rolesetoperations.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/rolesetoperations.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/suite_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/suite_test.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/sync.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/sync.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/sync_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/sync_test.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/utils.go -------------------------------------------------------------------------------- /pkg/controller/stormservice/utils_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/stormservice/utils_test.go -------------------------------------------------------------------------------- /pkg/controller/util/controller_utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/controller_utils.go -------------------------------------------------------------------------------- /pkg/controller/util/controller_utils_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/controller_utils_test.go -------------------------------------------------------------------------------- /pkg/controller/util/expectation/expectation.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/expectation/expectation.go -------------------------------------------------------------------------------- /pkg/controller/util/history/controller_history.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/history/controller_history.go -------------------------------------------------------------------------------- /pkg/controller/util/orchestration/util.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/orchestration/util.go -------------------------------------------------------------------------------- /pkg/controller/util/orchestration/util_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/orchestration/util_test.go -------------------------------------------------------------------------------- /pkg/controller/util/patch/json_patch.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/patch/json_patch.go -------------------------------------------------------------------------------- /pkg/controller/util/patch/json_patch_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/patch/json_patch_test.go -------------------------------------------------------------------------------- /pkg/controller/util/patch/patch_method.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/patch/patch_method.go -------------------------------------------------------------------------------- /pkg/controller/util/patch/patch_method_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/controller/util/patch/patch_method_test.go -------------------------------------------------------------------------------- /pkg/features/features.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/features/features.go -------------------------------------------------------------------------------- /pkg/kvevent/doc.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/doc.go -------------------------------------------------------------------------------- /pkg/kvevent/errors.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/errors.go -------------------------------------------------------------------------------- /pkg/kvevent/handler.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/handler.go -------------------------------------------------------------------------------- /pkg/kvevent/handler_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/handler_test.go -------------------------------------------------------------------------------- /pkg/kvevent/integration_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/integration_test.go -------------------------------------------------------------------------------- /pkg/kvevent/interfaces.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/interfaces.go -------------------------------------------------------------------------------- /pkg/kvevent/manager.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/manager.go -------------------------------------------------------------------------------- /pkg/kvevent/manager_comprehensive_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/manager_comprehensive_test.go -------------------------------------------------------------------------------- /pkg/kvevent/manager_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/manager_test.go -------------------------------------------------------------------------------- /pkg/kvevent/test_helpers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/kvevent/test_helpers.go -------------------------------------------------------------------------------- /pkg/metrics/common.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/common.go -------------------------------------------------------------------------------- /pkg/metrics/custom_metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/custom_metrics.go -------------------------------------------------------------------------------- /pkg/metrics/custom_metrics_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/custom_metrics_test.go -------------------------------------------------------------------------------- /pkg/metrics/engine_fetcher.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/engine_fetcher.go -------------------------------------------------------------------------------- /pkg/metrics/engine_fetcher_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/engine_fetcher_test.go -------------------------------------------------------------------------------- /pkg/metrics/metrics.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/metrics.go -------------------------------------------------------------------------------- /pkg/metrics/server.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/server.go -------------------------------------------------------------------------------- /pkg/metrics/types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/types.go -------------------------------------------------------------------------------- /pkg/metrics/types_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/types_test.go -------------------------------------------------------------------------------- /pkg/metrics/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/utils.go -------------------------------------------------------------------------------- /pkg/metrics/utils_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/metrics/utils_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/README.md -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/algorithms_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/algorithms_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/fallback.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/fallback.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/fallback_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/fallback_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_busy_time.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_busy_time.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_gpu_cache.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_gpu_cache.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_kv_cache.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_kv_cache.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_latency.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_latency.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_load.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_load.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_load_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_load_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_request.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_request.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_util.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_util.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/least_util_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/least_util_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/pack_load.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/pack_load.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/prefix_cache.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/prefix_cache.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/queue_router.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/queue_router.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/random.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/random.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/router.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/router.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/router_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/router_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/slo.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/slo.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/slo_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/slo_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/throughput.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/throughput.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/throughput_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/throughput_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/tokenizer_pool.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/tokenizer_pool.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/util.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/util.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/vtc.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/vtc.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/vtc/vtc_basic.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/vtc/vtc_basic.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/algorithms/vtc/vtc_router.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/algorithms/vtc/vtc_router.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_ratelimit.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_ratelimit.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_req_body.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_req_body.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_req_body_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_req_body_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_req_headers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_req_headers.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_req_headers_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_req_headers_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_rsp_body.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_rsp_body.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_rsp_headers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_rsp_headers.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_rsp_headers_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_rsp_headers_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/gateway_test_helpers.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/gateway_test_helpers.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/queue/queue_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/queue/queue_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/queue/simple_queue.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/queue/simple_queue.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/queue/simple_queue_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/queue/simple_queue_test.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/queue/slo_queue.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/queue/slo_queue.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/ratelimiter/rate_limiter.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/ratelimiter/rate_limiter.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/ratelimiter/redis.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/ratelimiter/redis.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/types.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/util.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/util.go -------------------------------------------------------------------------------- /pkg/plugins/gateway/util_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/plugins/gateway/util_test.go -------------------------------------------------------------------------------- /pkg/types/output_predictor.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/output_predictor.go -------------------------------------------------------------------------------- /pkg/types/pod_list.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/pod_list.go -------------------------------------------------------------------------------- /pkg/types/router.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/router.go -------------------------------------------------------------------------------- /pkg/types/router_context.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/router_context.go -------------------------------------------------------------------------------- /pkg/types/router_context_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/router_context_test.go -------------------------------------------------------------------------------- /pkg/types/router_queue.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/router_queue.go -------------------------------------------------------------------------------- /pkg/types/types_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/types/types_test.go -------------------------------------------------------------------------------- /pkg/utils/annotations.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/annotations.go -------------------------------------------------------------------------------- /pkg/utils/annotations_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/annotations_test.go -------------------------------------------------------------------------------- /pkg/utils/hash/hash.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/hash/hash.go -------------------------------------------------------------------------------- /pkg/utils/hash/hash_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/hash/hash_test.go -------------------------------------------------------------------------------- /pkg/utils/kvcache.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/kvcache.go -------------------------------------------------------------------------------- /pkg/utils/kvcache_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/kvcache_test.go -------------------------------------------------------------------------------- /pkg/utils/labels.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/labels.go -------------------------------------------------------------------------------- /pkg/utils/labels_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/labels_test.go -------------------------------------------------------------------------------- /pkg/utils/lrustore/lru_store.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/lrustore/lru_store.go -------------------------------------------------------------------------------- /pkg/utils/lrustore/lru_store_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/lrustore/lru_store_test.go -------------------------------------------------------------------------------- /pkg/utils/lrustore/store.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/lrustore/store.go -------------------------------------------------------------------------------- /pkg/utils/modeladapter.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/modeladapter.go -------------------------------------------------------------------------------- /pkg/utils/modeladapter_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/modeladapter_test.go -------------------------------------------------------------------------------- /pkg/utils/pod.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/pod.go -------------------------------------------------------------------------------- /pkg/utils/pod_array.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/pod_array.go -------------------------------------------------------------------------------- /pkg/utils/pod_array_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/pod_array_test.go -------------------------------------------------------------------------------- /pkg/utils/pod_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/pod_test.go -------------------------------------------------------------------------------- /pkg/utils/prefixcacheindexer/hash.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/prefixcacheindexer/hash.go -------------------------------------------------------------------------------- /pkg/utils/prefixcacheindexer/hash_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/prefixcacheindexer/hash_test.go -------------------------------------------------------------------------------- /pkg/utils/prefixcacheindexer/tree.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/prefixcacheindexer/tree.go -------------------------------------------------------------------------------- /pkg/utils/prefixcacheindexer/tree_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/prefixcacheindexer/tree_test.go -------------------------------------------------------------------------------- /pkg/utils/raycluster.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/raycluster.go -------------------------------------------------------------------------------- /pkg/utils/redis.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/redis.go -------------------------------------------------------------------------------- /pkg/utils/registry.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/registry.go -------------------------------------------------------------------------------- /pkg/utils/registry_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/registry_test.go -------------------------------------------------------------------------------- /pkg/utils/sync_map.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/sync_map.go -------------------------------------------------------------------------------- /pkg/utils/sync_map_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/sync_map_test.go -------------------------------------------------------------------------------- /pkg/utils/syncprefixcacheindexer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/syncprefixcacheindexer/README.md -------------------------------------------------------------------------------- /pkg/utils/syncprefixcacheindexer/events.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/syncprefixcacheindexer/events.go -------------------------------------------------------------------------------- /pkg/utils/syncprefixcacheindexer/sync_hash.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/syncprefixcacheindexer/sync_hash.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/README.md -------------------------------------------------------------------------------- /pkg/utils/tokenizer/adapter_sglang.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/adapter_sglang.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/adapter_vllm.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/adapter_vllm.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/errors.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/errors.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/interfaces.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/interfaces.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/local_characters.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/local_characters.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/local_tiktoken.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/local_tiktoken.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/remote_client.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/remote_client.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/remote_client_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/remote_client_test.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/remote_tokenizer.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/remote_tokenizer.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/tokenizer.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/tokenizer.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/types.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/types.go -------------------------------------------------------------------------------- /pkg/utils/tokenizer/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/tokenizer/utils.go -------------------------------------------------------------------------------- /pkg/utils/users.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/users.go -------------------------------------------------------------------------------- /pkg/utils/util.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/util.go -------------------------------------------------------------------------------- /pkg/utils/util_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/util_test.go -------------------------------------------------------------------------------- /pkg/utils/utils_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/utils/utils_test.go -------------------------------------------------------------------------------- /pkg/webhook/deployment_webhook.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/webhook/deployment_webhook.go -------------------------------------------------------------------------------- /pkg/webhook/kvcache_webhook.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/webhook/kvcache_webhook.go -------------------------------------------------------------------------------- /pkg/webhook/modeladapter_webhook.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/webhook/modeladapter_webhook.go -------------------------------------------------------------------------------- /pkg/webhook/podautoscaler_webhook.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/webhook/podautoscaler_webhook.go -------------------------------------------------------------------------------- /pkg/webhook/sidecar_injection.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/webhook/sidecar_injection.go -------------------------------------------------------------------------------- /pkg/webhook/stormservice_webhook.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/pkg/webhook/stormservice_webhook.go -------------------------------------------------------------------------------- /python/aibrix/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/README.md -------------------------------------------------------------------------------- /python/aibrix/aibrix/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/__version__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/__version__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/app.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/README.md -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/constant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/constant.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/driver.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/job_driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/job_driver.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/job_entity/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/job_entity/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/job_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/job_manager.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/scheduler.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/storage/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/storage/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/storage/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/storage/adapter.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/batch/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/batch/worker.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/common/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/common/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/common/errors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/common/errors.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/config.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/__main__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/base.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/entity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/entity.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/huggingface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/huggingface.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/s3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/s3.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/tos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/tos.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/downloader/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/downloader/utils.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/envs.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/gpu_optimizer/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/gpu_optimizer/Makefile -------------------------------------------------------------------------------- /python/aibrix/aibrix/gpu_optimizer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/gpu_optimizer/README.md -------------------------------------------------------------------------------- /python/aibrix/aibrix/gpu_optimizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/gpu_optimizer/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/gpu_optimizer/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/gpu_optimizer/app.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/logger.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/api/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/api/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/api/v1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/api/v1/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/api/v1/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/api/v1/batch.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/api/v1/files.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/api/v1/files.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/api/v1/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/api/v1/models.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/api/v1/users.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/api/v1/users.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/app.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/cache/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/cache/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/cache/job.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/cache/job.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/cache/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/cache/utils.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/core/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/core/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/secret_gen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/secret_gen.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/setting/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/setting/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metadata/setting/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metadata/setting/config.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metrics/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metrics/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metrics/engine_rules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metrics/engine_rules.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metrics/http_collector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metrics/http_collector.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metrics/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metrics/metrics.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/metrics/standard_rules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/metrics/standard_rules.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/openapi/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/openapi/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/openapi/engine/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/openapi/engine/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/openapi/engine/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/openapi/engine/base.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/openapi/engine/vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/openapi/engine/vllm.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/openapi/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/openapi/model.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/openapi/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/openapi/protocol.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/protos/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/protos/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/runtime/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/runtime/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/runtime/artifact_service.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/runtime/artifact_service.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/runtime/downloaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/runtime/downloaders.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/__init__.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/base.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/factory.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/local.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/local.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/reader.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/redis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/redis.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/s3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/s3.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/tos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/tos.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/types.py -------------------------------------------------------------------------------- /python/aibrix/aibrix/storage/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/aibrix/storage/utils.py -------------------------------------------------------------------------------- /python/aibrix/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/poetry.lock -------------------------------------------------------------------------------- /python/aibrix/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/pyproject.toml -------------------------------------------------------------------------------- /python/aibrix/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/scripts/__init__.py -------------------------------------------------------------------------------- /python/aibrix/scripts/format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/scripts/format.sh -------------------------------------------------------------------------------- /python/aibrix/scripts/generate_secrets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/scripts/generate_secrets.py -------------------------------------------------------------------------------- /python/aibrix/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/__init__.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/aibrix/tests/batch/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/conftest.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/test_batch_endpoints.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/test_batch_endpoints.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/test_driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/test_driver.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/test_job_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/test_job_cache.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/test_job_entity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/test_job_entity.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/test_job_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/test_job_manager.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/test_rbac_setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/test_rbac_setup.py -------------------------------------------------------------------------------- /python/aibrix/tests/batch/testdata/job_rbac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/testdata/job_rbac.yaml -------------------------------------------------------------------------------- /python/aibrix/tests/batch/testdata/s3_secret.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/batch/testdata/s3_secret.yaml -------------------------------------------------------------------------------- /python/aibrix/tests/downloader/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/aibrix/tests/downloader/test_entity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/downloader/test_entity.py -------------------------------------------------------------------------------- /python/aibrix/tests/downloader/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/downloader/test_utils.py -------------------------------------------------------------------------------- /python/aibrix/tests/e2e/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/e2e/README.md -------------------------------------------------------------------------------- /python/aibrix/tests/e2e/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/e2e/__init__.py -------------------------------------------------------------------------------- /python/aibrix/tests/e2e/test_batch_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/e2e/test_batch_api.py -------------------------------------------------------------------------------- /python/aibrix/tests/gpu_optimizer/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /python/aibrix/tests/metadata/test_models_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/metadata/test_models_api.py -------------------------------------------------------------------------------- /python/aibrix/tests/metadata/test_secret_gen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/metadata/test_secret_gen.py -------------------------------------------------------------------------------- /python/aibrix/tests/metadata/test_users_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/metadata/test_users_api.py -------------------------------------------------------------------------------- /python/aibrix/tests/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/aibrix/tests/metrics/test_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/metrics/test_metrics.py -------------------------------------------------------------------------------- /python/aibrix/tests/openapi/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/aibrix/tests/openapi/engine/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/aibrix/tests/storage/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/README.md -------------------------------------------------------------------------------- /python/aibrix/tests/storage/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/__init__.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/conftest.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_factory.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_local_storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_local_storage.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_reader.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_redis_storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_redis_storage.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_s3_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_s3_demo.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_storage.py -------------------------------------------------------------------------------- /python/aibrix/tests/storage/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/storage/test_utils.py -------------------------------------------------------------------------------- /python/aibrix/tests/test_files_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/test_files_api.py -------------------------------------------------------------------------------- /python/aibrix/tests/test_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix/tests/test_logger.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/.gitignore -------------------------------------------------------------------------------- /python/aibrix_kvcache/.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/.pre-commit-config.yaml -------------------------------------------------------------------------------- /python/aibrix_kvcache/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/CMakeLists.txt -------------------------------------------------------------------------------- /python/aibrix_kvcache/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/LICENSE -------------------------------------------------------------------------------- /python/aibrix_kvcache/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/README.md -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/__init__.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/config.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/envs.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/metrics.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/profiling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/profiling.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/spec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/spec.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/status.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/status.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/utils.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/aibrix_kvcache/version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/aibrix_kvcache/version.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/cmake/utils.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/cmake/utils.cmake -------------------------------------------------------------------------------- /python/aibrix_kvcache/csrc/cache.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/csrc/cache.h -------------------------------------------------------------------------------- /python/aibrix_kvcache/csrc/cache_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/csrc/cache_kernels.cu -------------------------------------------------------------------------------- /python/aibrix_kvcache/csrc/core/registration.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/csrc/core/registration.h -------------------------------------------------------------------------------- /python/aibrix_kvcache/csrc/torch_bindings.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/csrc/torch_bindings.cpp -------------------------------------------------------------------------------- /python/aibrix_kvcache/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/pyproject.toml -------------------------------------------------------------------------------- /python/aibrix_kvcache/requirements/build.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/requirements/build.txt -------------------------------------------------------------------------------- /python/aibrix_kvcache/requirements/core.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/requirements/core.txt -------------------------------------------------------------------------------- /python/aibrix_kvcache/requirements/dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/requirements/dev.txt -------------------------------------------------------------------------------- /python/aibrix_kvcache/requirements/lint.txt: -------------------------------------------------------------------------------- 1 | # formatting 2 | pre-commit==4.0.1 3 | -------------------------------------------------------------------------------- /python/aibrix_kvcache/requirements/test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/requirements/test.txt -------------------------------------------------------------------------------- /python/aibrix_kvcache/scripts/format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/scripts/format.sh -------------------------------------------------------------------------------- /python/aibrix_kvcache/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/setup.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/__init__.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/conftest.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/pytest.ini -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_cache_handle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_cache_handle.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_cache_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_cache_manager.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_cache_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_cache_ops.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_common.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_key_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_key_builder.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_l1cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_l1cache.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_l2cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_l2cache.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_memory_region.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_memory_region.py -------------------------------------------------------------------------------- /python/aibrix_kvcache/tests/test_placement.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/python/aibrix_kvcache/tests/test_placement.py -------------------------------------------------------------------------------- /samples/adapter/adapter-api-key.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/adapter/adapter-api-key.yaml -------------------------------------------------------------------------------- /samples/adapter/adapter-multi-replica.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/adapter/adapter-multi-replica.yaml -------------------------------------------------------------------------------- /samples/adapter/adapter.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/adapter/adapter.yaml -------------------------------------------------------------------------------- /samples/adapter/base-api-key.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/adapter/base-api-key.yaml -------------------------------------------------------------------------------- /samples/adapter/base-without-runtime.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/adapter/base-without-runtime.yaml -------------------------------------------------------------------------------- /samples/adapter/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/adapter/base.yaml -------------------------------------------------------------------------------- /samples/ai-gateway-integration/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/ai-gateway-integration/README.md -------------------------------------------------------------------------------- /samples/ai-gateway-integration/gateway.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/ai-gateway-integration/gateway.yaml -------------------------------------------------------------------------------- /samples/ai-gateway-integration/llama-7b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/ai-gateway-integration/llama-7b.yaml -------------------------------------------------------------------------------- /samples/ai-gateway-integration/mistral-7b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/ai-gateway-integration/mistral-7b.yaml -------------------------------------------------------------------------------- /samples/autoscaling/apa-resource.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/apa-resource.yaml -------------------------------------------------------------------------------- /samples/autoscaling/apa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/apa.yaml -------------------------------------------------------------------------------- /samples/autoscaling/deploy.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/deploy.yaml -------------------------------------------------------------------------------- /samples/autoscaling/hpa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/hpa.yaml -------------------------------------------------------------------------------- /samples/autoscaling/kpa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/kpa.yaml -------------------------------------------------------------------------------- /samples/autoscaling/multimetrics-apa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/multimetrics-apa.yaml -------------------------------------------------------------------------------- /samples/autoscaling/optimizer-kpa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/optimizer-kpa.yaml -------------------------------------------------------------------------------- /samples/autoscaling/stormservice-pool.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/stormservice-pool.yaml -------------------------------------------------------------------------------- /samples/autoscaling/stormservice-replica.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/autoscaling/stormservice-replica.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/README.md -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-ai-runtime.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-ai-runtime.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-autoscaling.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-autoscaling.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-huggingface.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-huggingface.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-local-nvme.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-local-nvme.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-pvc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-pvc.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-service.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-service.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/deepseek-r1-tcp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/deepseek-r1-tcp.yaml -------------------------------------------------------------------------------- /samples/deepseek-r1/static/deepseek-dashboard.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/deepseek-r1/static/deepseek-dashboard.png -------------------------------------------------------------------------------- /samples/disaggregation/sglang/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/sglang/README.md -------------------------------------------------------------------------------- /samples/disaggregation/sglang/pool.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/sglang/pool.yaml -------------------------------------------------------------------------------- /samples/disaggregation/sglang/replica.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/sglang/replica.yaml -------------------------------------------------------------------------------- /samples/disaggregation/sglang/tp-1p1d.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/sglang/tp-1p1d.yaml -------------------------------------------------------------------------------- /samples/disaggregation/vllm/1p1d.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/vllm/1p1d.yaml -------------------------------------------------------------------------------- /samples/disaggregation/vllm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/vllm/README.md -------------------------------------------------------------------------------- /samples/disaggregation/vllm/pool.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/vllm/pool.yaml -------------------------------------------------------------------------------- /samples/disaggregation/vllm/replica.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/vllm/replica.yaml -------------------------------------------------------------------------------- /samples/disaggregation/vllm/router.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/disaggregation/vllm/router.yaml -------------------------------------------------------------------------------- /samples/distributed/fleet-two-node.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/distributed/fleet-two-node.yaml -------------------------------------------------------------------------------- /samples/distributed/fleet.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/distributed/fleet.yaml -------------------------------------------------------------------------------- /samples/heterogeneous/kustomization.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/heterogeneous/kustomization.yaml -------------------------------------------------------------------------------- /samples/kvcache/infinistore/kvcache.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/infinistore/kvcache.yaml -------------------------------------------------------------------------------- /samples/kvcache/infinistore/vllm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/infinistore/vllm.yaml -------------------------------------------------------------------------------- /samples/kvcache/l1cache/vllm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/l1cache/vllm.yaml -------------------------------------------------------------------------------- /samples/kvcache/profiling/profiling_svc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/profiling/profiling_svc.yaml -------------------------------------------------------------------------------- /samples/kvcache/vineyard/deployment-tp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/vineyard/deployment-tp.yaml -------------------------------------------------------------------------------- /samples/kvcache/vineyard/deployment.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/vineyard/deployment.yaml -------------------------------------------------------------------------------- /samples/kvcache/vineyard/kvcache-tp.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/vineyard/kvcache-tp.yaml -------------------------------------------------------------------------------- /samples/kvcache/vineyard/kvcache.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/kvcache/vineyard/kvcache.yaml -------------------------------------------------------------------------------- /samples/multimodality/vllm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/vllm/README.md -------------------------------------------------------------------------------- /samples/multimodality/vllm/dse-qwen2-2b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/vllm/dse-qwen2-2b.yaml -------------------------------------------------------------------------------- /samples/multimodality/vllm/llava-7b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/vllm/llava-7b.yaml -------------------------------------------------------------------------------- /samples/multimodality/vllm/qwen-audio.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/vllm/qwen-audio.yaml -------------------------------------------------------------------------------- /samples/multimodality/vllm/qwen-vl.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/vllm/qwen-vl.yaml -------------------------------------------------------------------------------- /samples/multimodality/vllm/send_file_base64.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/vllm/send_file_base64.py -------------------------------------------------------------------------------- /samples/multimodality/xDiT/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/multimodality/xDiT/README.md -------------------------------------------------------------------------------- /samples/quickstart/model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/quickstart/model.yaml -------------------------------------------------------------------------------- /samples/quickstart/pd-model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/quickstart/pd-model.yaml -------------------------------------------------------------------------------- /samples/quickstart/vke/model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/quickstart/vke/model.yaml -------------------------------------------------------------------------------- /samples/quickstart/vke/pd-model.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/quickstart/vke/pd-model.yaml -------------------------------------------------------------------------------- /samples/volcano-engine/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/README.md -------------------------------------------------------------------------------- /samples/volcano-engine/autoscaler.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/autoscaler.yaml -------------------------------------------------------------------------------- /samples/volcano-engine/deepseek-8b-naive.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/deepseek-8b-naive.yaml -------------------------------------------------------------------------------- /samples/volcano-engine/deepseek-r1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/deepseek-r1.yaml -------------------------------------------------------------------------------- /samples/volcano-engine/grafana.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/grafana.yaml -------------------------------------------------------------------------------- /samples/volcano-engine/hpa-r1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/hpa-r1.yaml -------------------------------------------------------------------------------- /samples/volcano-engine/kvcache.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/samples/volcano-engine/kvcache.yaml -------------------------------------------------------------------------------- /scripts/port-forward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/scripts/port-forward.sh -------------------------------------------------------------------------------- /test/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/README.md -------------------------------------------------------------------------------- /test/e2e/e2e_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/e2e/e2e_test.go -------------------------------------------------------------------------------- /test/e2e/model_adapter_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/e2e/model_adapter_test.go -------------------------------------------------------------------------------- /test/e2e/openai_api_compatibility_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/e2e/openai_api_compatibility_test.go -------------------------------------------------------------------------------- /test/e2e/routing_strategy_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/e2e/routing_strategy_test.go -------------------------------------------------------------------------------- /test/e2e/util.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/e2e/util.go -------------------------------------------------------------------------------- /test/e2e/vtc_routing_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/e2e/vtc_routing_test.go -------------------------------------------------------------------------------- /test/integration/controller/podset_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/controller/podset_test.go -------------------------------------------------------------------------------- /test/integration/controller/roleset_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/controller/roleset_test.go -------------------------------------------------------------------------------- /test/integration/controller/suit_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/controller/suit_test.go -------------------------------------------------------------------------------- /test/integration/engine/lora/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/engine/lora/README.md -------------------------------------------------------------------------------- /test/integration/engine/lora/run_all_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/engine/lora/run_all_tests.py -------------------------------------------------------------------------------- /test/integration/engine/lora/test_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/engine/lora/test_api.py -------------------------------------------------------------------------------- /test/integration/engine/lora/test_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/engine/lora/test_config.py -------------------------------------------------------------------------------- /test/integration/engine/lora/test_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/engine/lora/test_memory.py -------------------------------------------------------------------------------- /test/integration/webhook/modeladapter_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/webhook/modeladapter_test.go -------------------------------------------------------------------------------- /test/integration/webhook/suit_test.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/integration/webhook/suit_test.go -------------------------------------------------------------------------------- /test/kv-event-sync-e2e.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/kv-event-sync-e2e.rst -------------------------------------------------------------------------------- /test/regression/v0.2.1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/README.md -------------------------------------------------------------------------------- /test/regression/v0.2.1/aibrix_naive.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/aibrix_naive.yaml -------------------------------------------------------------------------------- /test/regression/v0.2.1/client.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/client.yaml -------------------------------------------------------------------------------- /test/regression/v0.2.1/k8s_stack.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/k8s_stack.yaml -------------------------------------------------------------------------------- /test/regression/v0.2.1/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/plot.py -------------------------------------------------------------------------------- /test/regression/v0.2.1/ps_k8s_stack.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/ps_k8s_stack.yaml -------------------------------------------------------------------------------- /test/regression/v0.2.1/ps_stack.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.2.1/ps_stack.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/README.md -------------------------------------------------------------------------------- /test/regression/v0.3.0/aibrix_naive.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/aibrix_naive.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/client.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/client.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/infinistore.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/infinistore.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/k8s_stack.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/k8s_stack.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/kvcache.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/kvcache.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/lmcache_helm_naive.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/lmcache_helm_naive.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/lmcache_helm_stack.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/lmcache_helm_stack.yaml -------------------------------------------------------------------------------- /test/regression/v0.3.0/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/plot.py -------------------------------------------------------------------------------- /test/regression/v0.3.0/ps_stack.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.3.0/ps_stack.yaml -------------------------------------------------------------------------------- /test/regression/v0.4.0/Chart.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.4.0/Chart.yaml -------------------------------------------------------------------------------- /test/regression/v0.4.0/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.4.0/README.md -------------------------------------------------------------------------------- /test/regression/v0.4.0/benchmark-client.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.4.0/benchmark-client.yaml -------------------------------------------------------------------------------- /test/regression/v0.4.0/dynamo/disagg.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.4.0/dynamo/disagg.yaml -------------------------------------------------------------------------------- /test/regression/v0.4.0/templates/_helpers.tpl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.4.0/templates/_helpers.tpl -------------------------------------------------------------------------------- /test/regression/v0.4.0/values.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.4.0/values.yaml -------------------------------------------------------------------------------- /test/regression/v0.5.0/sglang-xpyd-rdma.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.5.0/sglang-xpyd-rdma.yaml -------------------------------------------------------------------------------- /test/regression/v0.5.0/vllm-xpyd-rdma.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/regression/v0.5.0/vllm-xpyd-rdma.yaml -------------------------------------------------------------------------------- /test/run-e2e-tests.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/run-e2e-tests.sh -------------------------------------------------------------------------------- /test/utils/utils.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/utils.go -------------------------------------------------------------------------------- /test/utils/validation/hpa.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/validation/hpa.go -------------------------------------------------------------------------------- /test/utils/validation/pod.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/validation/pod.go -------------------------------------------------------------------------------- /test/utils/validation/podautoscaler.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/validation/podautoscaler.go -------------------------------------------------------------------------------- /test/utils/validation/podset.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/validation/podset.go -------------------------------------------------------------------------------- /test/utils/validation/roleset.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/validation/roleset.go -------------------------------------------------------------------------------- /test/utils/validation/stormservice.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/validation/stormservice.go -------------------------------------------------------------------------------- /test/utils/wrapper/deployment.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/deployment.go -------------------------------------------------------------------------------- /test/utils/wrapper/kvcache.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/kvcache.go -------------------------------------------------------------------------------- /test/utils/wrapper/modeladapter.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/modeladapter.go -------------------------------------------------------------------------------- /test/utils/wrapper/podautoscaler.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/podautoscaler.go -------------------------------------------------------------------------------- /test/utils/wrapper/podset.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/podset.go -------------------------------------------------------------------------------- /test/utils/wrapper/roleset.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/roleset.go -------------------------------------------------------------------------------- /test/utils/wrapper/stormservice.go: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vllm-project/aibrix/HEAD/test/utils/wrapper/stormservice.go --------------------------------------------------------------------------------