├── .github ├── CODEOWNERS ├── dependabot.yml └── workflows │ └── build.yml ├── .gitignore ├── Dockerfile ├── LICENSE ├── README.md ├── babel.config.js ├── docker-bake.hcl ├── docs ├── 01-getting-started │ ├── 01-installation │ │ ├── 01-gpu.md │ │ ├── 02-cpu.md │ │ ├── 03-ai-accelerator.md │ │ └── README.md │ ├── 02-quickstart.md │ ├── 03-examples │ │ ├── 01-offline-inference │ │ │ ├── 01-audio_language.md │ │ │ ├── 02-basic.md │ │ │ ├── 03-chat_with_tools.md │ │ │ ├── 04-cpu_offload_lmcache.md │ │ │ ├── 05-data_parallel.md │ │ │ ├── 06-disaggregated_prefill_lmcache.md │ │ │ ├── 07-disaggregated_prefill.md │ │ │ ├── 08-distributed.md │ │ │ ├── 09-eagle.md │ │ │ ├── 10-encoder_decoder_multimodal.md │ │ │ ├── 11-encoder_decoder.md │ │ │ ├── 12-llm_engine_example.md │ │ │ ├── 13-load_sharded_state.md │ │ │ ├── 14-lora_with_quantization_inference.md │ │ │ ├── 15-mistral-small.md │ │ │ ├── 16-mlpspeculator.md │ │ │ ├── 17-multilora_inference.md │ │ │ ├── 18-neuron_int8_quantization.md │ │ │ ├── 19-neuron.md │ │ │ ├── 20-openai_batch.md │ │ │ ├── 21-prefix_caching.md │ │ │ ├── 22-prithvi_geospatial_mae.md │ │ │ ├── 23-profiling_tpu.md │ │ │ ├── 24-profiling.md │ │ │ ├── 25-reproduciblity.md │ │ │ ├── 26-rlhf.md │ │ │ ├── 27-rlhf_colocate.md │ │ │ ├── 28-rlhf_utils.md │ │ │ ├── 29-save_sharded_state.md │ │ │ ├── 30-simple_profiling.md │ │ │ ├── 31-structured_outputs.md │ │ │ ├── 32-torchrun_example.md │ │ │ ├── 33-tpu.md │ │ │ ├── 34-vision_language.md │ │ │ ├── 35-vision_language_embedding.md │ │ │ ├── 36-vision_language_multi_image.md │ │ │ └── README.md │ │ ├── 02-online-serving │ │ │ ├── 01-api_client.md │ │ │ ├── 02-chart-helm.md │ │ │ ├── 03-cohere_rerank_client.md │ │ │ ├── 04-disaggregated_prefill.md │ │ │ ├── 05-gradio_openai_chatbot_webserver.md │ │ │ ├── 06-gradio_webserver.md │ │ │ ├── 07-jinaai_rerank_client.md │ │ │ ├── 08-multi-node-serving.md │ │ │ ├── 09-openai_chat_completion_client.md │ │ │ ├── 10-openai_chat_completion_client_for_multimodal.md │ │ │ ├── 11-openai_chat_completion_client_with_tools.md │ │ │ ├── 12-openai_chat_completion_client_with_tools_required.md │ │ │ ├── 13-openai_chat_completion_structured_outputs.md │ │ │ ├── 14-openai_chat_completion_structured_outputs_with_reasoning.md │ │ │ ├── 15-openai_chat_completion_tool_calls_with_reasoning.md │ │ │ ├── 16-openai_chat_completion_with_reasoning.md │ │ │ ├── 17-openai_chat_completion_with_reasoning_streaming.md │ │ │ ├── 18-openai_chat_embedding_client_for_multimodal.md │ │ │ ├── 19-openai_completion_client.md │ │ │ ├── 20-openai_cross_encoder_score.md │ │ │ ├── 21-openai_embedding_client.md │ │ │ ├── 22-openai_pooling_client.md │ │ │ ├── 23-openai_transcription_client.md │ │ │ ├── 24-opentelemetry.md │ │ │ ├── 25-prometheus_grafana.md │ │ │ ├── 26-run_cluster.md │ │ │ ├── 27-sagemaker-entrypoint.md │ │ │ ├── README.md │ │ │ └── img │ │ │ │ ├── opentelemetry_1.png │ │ │ │ ├── opentelemetry_2.png │ │ │ │ ├── opentelemetry_3.png │ │ │ │ └── prometheus_grafana_1.png │ │ └── 03-other │ │ │ ├── 01-logging_configuration.md │ │ │ ├── 02-tensorize_vllm_model.md │ │ │ └── README.md │ ├── 04-troubleshooting.md │ ├── 05-faq.md │ ├── 06-v1-user-guide.md │ └── _category_.json ├── 02-models │ ├── 01-supported_models.md │ ├── 02-generative_models.md │ ├── 03-Pooling Models.md │ ├── 04-extensions │ │ ├── 01-runai_model_streamer.md │ │ ├── 02-tensorizer.md │ │ ├── 03-fastsafetensor.md │ │ └── README.md │ └── _category_.json ├── 03-features │ ├── 01-quantization │ │ ├── 01-supported_hardware.md │ │ ├── 02-auto_awq.md │ │ ├── 03-bnb.md │ │ ├── 04-gguf.md │ │ ├── 05-gptqmodel.md │ │ ├── 06-int4.md │ │ ├── 07-int8.md │ │ ├── 08-fp8.md │ │ ├── 09-quantized_kvcache.md │ │ ├── 10-TorchAO.md │ │ └── README.md │ ├── 02-lora.md │ ├── 03-tool_calling.md │ ├── 04-reasoning_outputs.md │ ├── 05-structured_outputs.md │ ├── 06-automatic_prefix_caching.md │ ├── 07-disagg_prefill.md │ ├── 08-spec_decode.md │ ├── 09-compatibility_matrix.md │ └── _category_.json ├── 04-training │ ├── 01-trl.md │ ├── 02-rlhf.md │ └── _category_.json ├── 05-inference-and-serving │ ├── 01-offline_inference.md │ ├── 02-openai_compatible_server.md │ ├── 03-multimodal_inputs.md │ ├── 04-distributed_serving_new.md │ ├── 05-metrics.md │ ├── 06-engine_args.md │ ├── 07-env_vars.md │ ├── 08-usage_stats.md │ ├── 09-integrations │ │ ├── 01-langchain.md │ │ ├── 02-llamaindex.md │ │ └── README.md │ └── _category_.json ├── 06-deployment │ ├── 01-docker.md │ ├── 02-k8s.md │ ├── 03-nginx.md │ ├── 04-framworks │ │ ├── 01-bentoml.md │ │ ├── 02-cerebrium.md │ │ ├── 03-dstack.md │ │ ├── 04-helm.md │ │ ├── 05-lws.md │ │ ├── 06-modal.md │ │ ├── 07-skypilot.md │ │ ├── 08-triton.md │ │ └── README.md │ ├── 05-integrations │ │ ├── 01-kserve.md │ │ ├── 02-kubeai.md │ │ ├── 03-llamastack.md │ │ ├── 04-llmaz.md │ │ ├── 05-production-stack.md │ │ └── README.md │ └── _category_.json ├── 07-performance │ ├── 01-optimization.md │ ├── 02-benchmarks.md │ └── _category_.json ├── 08-design │ ├── 01-arch_overview.md │ ├── 02-huggingface_integration.md │ ├── 03-plugin_system.md │ ├── 04-paged_attention.md │ ├── 05-mm_processing.md │ ├── 06-automatic_prefix_caching.md │ ├── 07-multiprocessing.md │ └── _category_.json ├── 09-design-v1 │ ├── 01-torch_compile.md │ ├── 02-prefix_caching.md │ ├── 03-metrics.md │ └── _category_.json ├── 10-contributing │ ├── 01-overview.md │ ├── 02-profiling_index.md │ ├── 03-dockerfile.md │ ├── 04-model │ │ ├── 01-basic.md │ │ ├── 02-registration.md │ │ ├── 03-tests.md │ │ ├── 04-multimodal.md │ │ └── README.md │ ├── 05-vulnerability_management.md │ └── _category_.json ├── 11-api │ ├── 01-offline_interence │ │ ├── 01-llm.md │ │ ├── 02-llm_inputs.md │ │ └── README.md │ ├── 02-engine │ │ ├── 01-llm_engine.md │ │ ├── 02-async_llm_engine.md │ │ └── README.md │ ├── 03-inference_params.md │ ├── 04-multimodal │ │ ├── 01-inputs.md │ │ ├── 02-parse.md │ │ ├── 03-processing.md │ │ ├── 04-profiling.md │ │ ├── 05-registry.md │ │ └── README.md │ ├── 05-model │ │ ├── 01-interfaces_base.md │ │ ├── 02-interfaces.md │ │ └── 03-adapters.md │ └── _category_.json ├── 12-community │ ├── 01-blog.md │ ├── 02-meetups.md │ ├── 03-sponsors.md │ └── _category_.json ├── 13-vllm-tutorials │ ├── 01-vLLM-stepbysteb.md │ ├── 02-infer-34b-with-vllm.md │ ├── 03-few-shot-w-qwen2-5.md │ ├── 04-vllm-langchain-tutorial.md │ └── _category_.json └── index.md ├── docusaurus.config.ts ├── nginx.conf ├── package.json ├── pnpm-lock.yaml ├── sidebars.ts ├── src ├── components │ └── HomepageFeatures │ │ ├── index.tsx │ │ └── styles.module.css ├── css │ └── custom.css └── pages │ ├── about.md │ ├── index.module.css │ ├── index.tsx │ └── markdown-page.md ├── static ├── .nojekyll └── img │ ├── 1-High-efficiency.svg │ ├── 2Memory-Management.svg │ ├── 3-Flexible-user-friendly.svg │ ├── docs │ ├── 02-07 │ │ ├── 01-Deploying&scaling-up-with-SkyPilot.png │ │ ├── 05-Deploying-with-Cerebrium.png │ │ └── 07-Deploying-with-dstack.png │ ├── 02-tutorials │ │ ├── api_path.png │ │ ├── bangding.png │ │ ├── curl_res.png │ │ ├── curl_res_local.png │ │ ├── id.png │ │ ├── model.png │ │ ├── res_api.png │ │ └── start.png │ ├── 07-03 │ │ └── Overview_of_the_step.png │ ├── 07-04 │ │ ├── k_vecs.png │ │ ├── key.png │ │ ├── logits_vec.png │ │ ├── q_vecs.png │ │ ├── query.png │ │ ├── v_vec.png │ │ └── value.png │ ├── 07-07 │ │ └── dockerfile-stages-dependency.png │ ├── v1-API │ │ └── 01-llm_engine_1.png │ ├── v1-Developer_Guide │ │ ├── 02-profiling_index_1.png │ │ └── 03-dockerfile_1.png │ ├── v1-deployment │ │ ├── 02-cerebrium_1.png │ │ ├── 03-dstack_1.png │ │ ├── 04-helm_1.png │ │ └── 07-skypilot_1.png │ ├── v1-design │ │ ├── 01-arch_overview_1.png │ │ ├── 01-arch_overview_2.png │ │ ├── 01-arch_overview_3.png │ │ ├── 04-paged_attention_1.png │ │ ├── 04-paged_attention_2.png │ │ ├── 04-paged_attention_3.png │ │ ├── 04-paged_attention_4.png │ │ ├── 04-paged_attention_5.jpg │ │ ├── 04-paged_attention_6.png │ │ └── 04-paged_attention_7.jpg │ ├── v1-design_v1 │ │ ├── 02-prefix_caching_1.png │ │ ├── 02-prefix_caching_2.png │ │ ├── 02-prefix_caching_3.png │ │ ├── 02-prefix_caching_4.png │ │ ├── 02-prefix_caching_5.png │ │ ├── 02-prefix_caching_6.png │ │ ├── 02-prefix_caching_7.png │ │ ├── 02-prefix_caching_8.png │ │ ├── 03-metrics_1.png │ │ ├── 03-metrics_2.png │ │ └── 03-metrics_3.png │ └── v1-features │ │ ├── 07-disagg_prefill_1.jpg │ │ └── 07-disagg_prefill_2.jpg │ ├── docusaurus-social-card.jpg │ ├── docusaurus.png │ ├── favicon.ico │ ├── logo.svg │ ├── undraw_docusaurus_mountain.svg │ ├── undraw_docusaurus_react.svg │ ├── undraw_docusaurus_tree.svg │ └── vllm-logo.png ├── tsconfig.json ├── versioned_docs └── version-0.8.x │ ├── 01-getting-started │ ├── 01-installation.md │ ├── 02-installation-with-rocm.md │ ├── 03-installation-with-openvino.md │ ├── 04-installation-with-cpu.md │ ├── 05-installation-with-neuron.md │ ├── 06-installation-with-tpu.md │ ├── 07-installation-with-xpu.md │ ├── 08-quickstart.md │ ├── 09-debugging-tips.md │ ├── 10-examples │ │ ├── 10-examples.md │ │ └── examples │ │ │ ├── 01-api_client.md │ │ │ ├── 02-aqlm_example.md │ │ │ ├── 03-cpu_offload.md │ │ │ ├── 04-gguf_inference.md │ │ │ ├── 05-gradio_openai_chatbot_webserver.md │ │ │ ├── 06-gradio_webserver.md │ │ │ ├── 07-llm_engine_example.md │ │ │ ├── 08-lora_with_quantization_inference.md │ │ │ ├── 09-multilora_inference.md │ │ │ ├── 10-offline_chat_with_tools.md │ │ │ ├── 11-offline_inference.md │ │ │ ├── 12-offline_inference_arctic.md │ │ │ ├── 13-offline_inference_audio_language.md │ │ │ ├── 14-offline_inference_chat.md │ │ │ ├── 15-offline_inference_distributed.md │ │ │ ├── 16-offline_inference_embedding.md │ │ │ ├── 17-offline_inference_encoder_decoder.md │ │ │ ├── 18-offline_inference_mlpspeculator.md │ │ │ ├── 19-offline_inference_neuron.md │ │ │ ├── 20-offline_inference_neuron_int8_quantization.md │ │ │ ├── 21-offline_inference_pixtral.md │ │ │ ├── 22-offline_inference_tpu.md │ │ │ ├── 23-offline_inference_vision_language.md │ │ │ ├── 24-offline_inference_vision_language_multi_image.md │ │ │ ├── 25-offline_inference_with_prefix.md │ │ │ ├── 26-offline_inference_with_profiler.md │ │ │ ├── 27-openai_audio_api_client.md │ │ │ ├── 28-openai_chat_completion_client.md │ │ │ ├── 29-openai_chat_completion_client_with_tools.md │ │ │ ├── 30-openai_completion_client.md │ │ │ ├── 31-openai_embedding_client.md │ │ │ ├── 32-openai_vision_api_client.md │ │ │ ├── 33-save_sharded_state.md │ │ │ └── 34-tensorize_vllm_model.md │ └── _category_.json │ ├── 02-serving │ ├── 01-openai-compatible-server.md │ ├── 02-deploying-with-docker.md │ ├── 03-distributed-inference-and-serving.md │ ├── 04-production-metrics.md │ ├── 05-environment-variables.md │ ├── 06-usage-stats-collection.md │ ├── 07-integrations │ │ ├── 01-deploying&scaling-up-with-skypilot.md │ │ ├── 02-deploying-with-kserve.md │ │ ├── 03-deploying-with-nvidia-triton.md │ │ ├── 04-deploying-with-bentoml.md │ │ ├── 05-deploying-with-cerebrium.md │ │ ├── 06-deploying-with-lws.md │ │ ├── 07-deploying-with-dstack.md │ │ ├── 08-serving-with-langchain.md │ │ ├── 09-serving-with-llama_index.md │ │ └── readme.md │ ├── 08-tensorizer.md │ ├── 09-compatibility matrix.md │ ├── 10-frequently-asked-questions.md │ └── _category_.json │ ├── 03-models │ ├── 01-supported-models.md │ ├── 02-adding-a-new-model.md │ ├── 03-enabling-multimodal-inputs.md │ ├── 04-engine-arguments.md │ ├── 05-using-lora-adapters.md │ ├── 06-using-vlms.md │ ├── 07-speculative-decoding-in-vllm.md │ ├── 08-performance-and-tuning.md │ └── _category_.json │ ├── 04-quantization │ ├── 01-supported_hardware.md │ ├── 02-autoawq.md │ ├── 03-bitsandbytes.md │ ├── 04-gguf.md │ ├── 05-int8-w8a8.md │ ├── 06-fp8-w8a8.md │ ├── 07-fp8-e5m2-kv-cache.md │ ├── 08-fp8-e4m3-kv-cache.md │ └── _category_.json │ ├── 05-automatic-prefix-caching │ ├── 01-introduction-apc.md │ ├── 02-implementation.md │ └── _category_.json │ ├── 06-performance-benchmarks │ ├── 06-benchmark-suites-of-vllm.md │ └── _category_.json │ ├── 07-developer-documentation │ ├── 01-sampling-parameters.md │ ├── 02-offline-inference │ │ ├── 01-llm-class.md │ │ ├── 02-llm-inputs.md │ │ └── readme.md │ ├── 03-vllm-engine │ │ ├── 01-llmengine.md │ │ ├── 02-asyncllmengine.md │ │ └── readme.md │ ├── 04-vllm-paged-attention.md │ ├── 05-input-processing │ │ ├── 01-model_inputs_index.md │ │ ├── 02-input-processing-pipeline.md │ │ └── _category_.json │ ├── 06-multi-modality │ │ ├── 01-adding-a-multimodal-plugin.md │ │ └── readme.md │ ├── 07-dockerfile.md │ ├── 08-profiling-vllm.md │ └── _category_.json │ ├── 08-indices-and-tables │ ├── 01-index.md │ ├── 02-python-module-index.md │ └── _category_.json │ ├── 09-community │ ├── 01-vllm-meetups.md │ ├── 02-sponsors.md │ └── _category_.json │ ├── 10-tutorials │ ├── 01-vLLM-stepbysteb.md │ ├── 02-infer-34b-with-vllm.md │ ├── 03-few-shot-w-qwen2-5.md │ └── 04-vllm-langchain-tutorial.md │ └── index.md ├── versioned_sidebars └── version-0.8.x-sidebars.json └── versions.json /.github/CODEOWNERS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/.github/CODEOWNERS -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/.github/dependabot.yml -------------------------------------------------------------------------------- /.github/workflows/build.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/.github/workflows/build.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/.gitignore -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/README.md -------------------------------------------------------------------------------- /babel.config.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/babel.config.js -------------------------------------------------------------------------------- /docker-bake.hcl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docker-bake.hcl -------------------------------------------------------------------------------- /docs/01-getting-started/01-installation/01-gpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/01-installation/01-gpu.md -------------------------------------------------------------------------------- /docs/01-getting-started/01-installation/02-cpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/01-installation/02-cpu.md -------------------------------------------------------------------------------- /docs/01-getting-started/01-installation/03-ai-accelerator.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/01-installation/03-ai-accelerator.md -------------------------------------------------------------------------------- /docs/01-getting-started/01-installation/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/01-installation/README.md -------------------------------------------------------------------------------- /docs/01-getting-started/02-quickstart.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/02-quickstart.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/01-audio_language.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/01-audio_language.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/02-basic.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/02-basic.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/03-chat_with_tools.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/03-chat_with_tools.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/04-cpu_offload_lmcache.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/04-cpu_offload_lmcache.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/05-data_parallel.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/05-data_parallel.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/06-disaggregated_prefill_lmcache.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/06-disaggregated_prefill_lmcache.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/07-disaggregated_prefill.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/07-disaggregated_prefill.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/08-distributed.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/08-distributed.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/09-eagle.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/09-eagle.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/10-encoder_decoder_multimodal.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/10-encoder_decoder_multimodal.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/11-encoder_decoder.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/11-encoder_decoder.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/12-llm_engine_example.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/12-llm_engine_example.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/13-load_sharded_state.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/13-load_sharded_state.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/14-lora_with_quantization_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/14-lora_with_quantization_inference.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/15-mistral-small.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/15-mistral-small.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/16-mlpspeculator.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/16-mlpspeculator.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/17-multilora_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/17-multilora_inference.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/18-neuron_int8_quantization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/18-neuron_int8_quantization.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/19-neuron.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/19-neuron.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/20-openai_batch.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/20-openai_batch.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/21-prefix_caching.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/21-prefix_caching.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/22-prithvi_geospatial_mae.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/22-prithvi_geospatial_mae.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/23-profiling_tpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/23-profiling_tpu.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/24-profiling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/24-profiling.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/25-reproduciblity.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/25-reproduciblity.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/26-rlhf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/26-rlhf.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/27-rlhf_colocate.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/27-rlhf_colocate.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/28-rlhf_utils.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/28-rlhf_utils.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/29-save_sharded_state.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/29-save_sharded_state.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/30-simple_profiling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/30-simple_profiling.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/31-structured_outputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/31-structured_outputs.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/32-torchrun_example.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/32-torchrun_example.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/33-tpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/33-tpu.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/34-vision_language.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/34-vision_language.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/35-vision_language_embedding.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/35-vision_language_embedding.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/36-vision_language_multi_image.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/36-vision_language_multi_image.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/01-offline-inference/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/01-offline-inference/README.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/01-api_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/01-api_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/02-chart-helm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/02-chart-helm.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/03-cohere_rerank_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/03-cohere_rerank_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/04-disaggregated_prefill.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/04-disaggregated_prefill.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/05-gradio_openai_chatbot_webserver.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/05-gradio_openai_chatbot_webserver.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/06-gradio_webserver.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/06-gradio_webserver.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/07-jinaai_rerank_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/07-jinaai_rerank_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/08-multi-node-serving.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/08-multi-node-serving.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/09-openai_chat_completion_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/09-openai_chat_completion_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/10-openai_chat_completion_client_for_multimodal.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/10-openai_chat_completion_client_for_multimodal.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/11-openai_chat_completion_client_with_tools.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/11-openai_chat_completion_client_with_tools.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/12-openai_chat_completion_client_with_tools_required.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/12-openai_chat_completion_client_with_tools_required.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/13-openai_chat_completion_structured_outputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/13-openai_chat_completion_structured_outputs.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/14-openai_chat_completion_structured_outputs_with_reasoning.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/14-openai_chat_completion_structured_outputs_with_reasoning.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/15-openai_chat_completion_tool_calls_with_reasoning.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/15-openai_chat_completion_tool_calls_with_reasoning.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/16-openai_chat_completion_with_reasoning.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/16-openai_chat_completion_with_reasoning.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/17-openai_chat_completion_with_reasoning_streaming.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/17-openai_chat_completion_with_reasoning_streaming.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/18-openai_chat_embedding_client_for_multimodal.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/18-openai_chat_embedding_client_for_multimodal.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/19-openai_completion_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/19-openai_completion_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/20-openai_cross_encoder_score.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/20-openai_cross_encoder_score.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/21-openai_embedding_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/21-openai_embedding_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/22-openai_pooling_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/22-openai_pooling_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/23-openai_transcription_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/23-openai_transcription_client.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/24-opentelemetry.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/24-opentelemetry.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/25-prometheus_grafana.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/25-prometheus_grafana.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/26-run_cluster.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/26-run_cluster.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/27-sagemaker-entrypoint.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/27-sagemaker-entrypoint.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/README.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/img/opentelemetry_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/img/opentelemetry_1.png -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/img/opentelemetry_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/img/opentelemetry_2.png -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/img/opentelemetry_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/img/opentelemetry_3.png -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/02-online-serving/img/prometheus_grafana_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/02-online-serving/img/prometheus_grafana_1.png -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/03-other/01-logging_configuration.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/03-other/01-logging_configuration.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/03-other/02-tensorize_vllm_model.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/03-other/02-tensorize_vllm_model.md -------------------------------------------------------------------------------- /docs/01-getting-started/03-examples/03-other/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/03-examples/03-other/README.md -------------------------------------------------------------------------------- /docs/01-getting-started/04-troubleshooting.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/04-troubleshooting.md -------------------------------------------------------------------------------- /docs/01-getting-started/05-faq.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/05-faq.md -------------------------------------------------------------------------------- /docs/01-getting-started/06-v1-user-guide.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/01-getting-started/06-v1-user-guide.md -------------------------------------------------------------------------------- /docs/01-getting-started/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "快速开始" 3 | } 4 | -------------------------------------------------------------------------------- /docs/02-models/01-supported_models.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/01-supported_models.md -------------------------------------------------------------------------------- /docs/02-models/02-generative_models.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/02-generative_models.md -------------------------------------------------------------------------------- /docs/02-models/03-Pooling Models.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/03-Pooling Models.md -------------------------------------------------------------------------------- /docs/02-models/04-extensions/01-runai_model_streamer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/04-extensions/01-runai_model_streamer.md -------------------------------------------------------------------------------- /docs/02-models/04-extensions/02-tensorizer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/04-extensions/02-tensorizer.md -------------------------------------------------------------------------------- /docs/02-models/04-extensions/03-fastsafetensor.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/04-extensions/03-fastsafetensor.md -------------------------------------------------------------------------------- /docs/02-models/04-extensions/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/02-models/04-extensions/README.md -------------------------------------------------------------------------------- /docs/02-models/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "支持模型" 3 | } 4 | -------------------------------------------------------------------------------- /docs/03-features/01-quantization/01-supported_hardware.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/01-supported_hardware.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/02-auto_awq.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/02-auto_awq.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/03-bnb.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/03-bnb.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/04-gguf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/04-gguf.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/05-gptqmodel.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/05-gptqmodel.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/06-int4.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/06-int4.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/07-int8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/07-int8.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/08-fp8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/08-fp8.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/09-quantized_kvcache.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/09-quantized_kvcache.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/10-TorchAO.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/10-TorchAO.md -------------------------------------------------------------------------------- /docs/03-features/01-quantization/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/01-quantization/README.md -------------------------------------------------------------------------------- /docs/03-features/02-lora.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/02-lora.md -------------------------------------------------------------------------------- /docs/03-features/03-tool_calling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/03-tool_calling.md -------------------------------------------------------------------------------- /docs/03-features/04-reasoning_outputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/04-reasoning_outputs.md -------------------------------------------------------------------------------- /docs/03-features/05-structured_outputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/05-structured_outputs.md -------------------------------------------------------------------------------- /docs/03-features/06-automatic_prefix_caching.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/06-automatic_prefix_caching.md -------------------------------------------------------------------------------- /docs/03-features/07-disagg_prefill.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/07-disagg_prefill.md -------------------------------------------------------------------------------- /docs/03-features/08-spec_decode.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/08-spec_decode.md -------------------------------------------------------------------------------- /docs/03-features/09-compatibility_matrix.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/03-features/09-compatibility_matrix.md -------------------------------------------------------------------------------- /docs/03-features/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "功能特性" 3 | } 4 | -------------------------------------------------------------------------------- /docs/04-training/01-trl.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/04-training/01-trl.md -------------------------------------------------------------------------------- /docs/04-training/02-rlhf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/04-training/02-rlhf.md -------------------------------------------------------------------------------- /docs/04-training/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "训练" 3 | } 4 | -------------------------------------------------------------------------------- /docs/05-inference-and-serving/01-offline_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/01-offline_inference.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/02-openai_compatible_server.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/02-openai_compatible_server.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/03-multimodal_inputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/03-multimodal_inputs.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/04-distributed_serving_new.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/04-distributed_serving_new.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/05-metrics.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/05-metrics.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/06-engine_args.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/06-engine_args.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/07-env_vars.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/07-env_vars.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/08-usage_stats.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/08-usage_stats.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/09-integrations/01-langchain.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/09-integrations/01-langchain.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/09-integrations/02-llamaindex.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/09-integrations/02-llamaindex.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/09-integrations/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/05-inference-and-serving/09-integrations/README.md -------------------------------------------------------------------------------- /docs/05-inference-and-serving/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "推理" 3 | } 4 | -------------------------------------------------------------------------------- /docs/06-deployment/01-docker.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/01-docker.md -------------------------------------------------------------------------------- /docs/06-deployment/02-k8s.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/02-k8s.md -------------------------------------------------------------------------------- /docs/06-deployment/03-nginx.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/03-nginx.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/01-bentoml.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/01-bentoml.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/02-cerebrium.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/02-cerebrium.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/03-dstack.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/03-dstack.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/04-helm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/04-helm.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/05-lws.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/05-lws.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/06-modal.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/06-modal.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/07-skypilot.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/07-skypilot.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/08-triton.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/08-triton.md -------------------------------------------------------------------------------- /docs/06-deployment/04-framworks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/04-framworks/README.md -------------------------------------------------------------------------------- /docs/06-deployment/05-integrations/01-kserve.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/05-integrations/01-kserve.md -------------------------------------------------------------------------------- /docs/06-deployment/05-integrations/02-kubeai.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/05-integrations/02-kubeai.md -------------------------------------------------------------------------------- /docs/06-deployment/05-integrations/03-llamastack.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/05-integrations/03-llamastack.md -------------------------------------------------------------------------------- /docs/06-deployment/05-integrations/04-llmaz.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/05-integrations/04-llmaz.md -------------------------------------------------------------------------------- /docs/06-deployment/05-integrations/05-production-stack.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/05-integrations/05-production-stack.md -------------------------------------------------------------------------------- /docs/06-deployment/05-integrations/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/06-deployment/05-integrations/README.md -------------------------------------------------------------------------------- /docs/06-deployment/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "部署" 3 | } 4 | -------------------------------------------------------------------------------- /docs/07-performance/01-optimization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/07-performance/01-optimization.md -------------------------------------------------------------------------------- /docs/07-performance/02-benchmarks.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/07-performance/02-benchmarks.md -------------------------------------------------------------------------------- /docs/07-performance/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "性能" 3 | } 4 | -------------------------------------------------------------------------------- /docs/08-design/01-arch_overview.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/01-arch_overview.md -------------------------------------------------------------------------------- /docs/08-design/02-huggingface_integration.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/02-huggingface_integration.md -------------------------------------------------------------------------------- /docs/08-design/03-plugin_system.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/03-plugin_system.md -------------------------------------------------------------------------------- /docs/08-design/04-paged_attention.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/04-paged_attention.md -------------------------------------------------------------------------------- /docs/08-design/05-mm_processing.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/05-mm_processing.md -------------------------------------------------------------------------------- /docs/08-design/06-automatic_prefix_caching.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/06-automatic_prefix_caching.md -------------------------------------------------------------------------------- /docs/08-design/07-multiprocessing.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/08-design/07-multiprocessing.md -------------------------------------------------------------------------------- /docs/08-design/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "设计文档" 3 | } 4 | -------------------------------------------------------------------------------- /docs/09-design-v1/01-torch_compile.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/09-design-v1/01-torch_compile.md -------------------------------------------------------------------------------- /docs/09-design-v1/02-prefix_caching.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/09-design-v1/02-prefix_caching.md -------------------------------------------------------------------------------- /docs/09-design-v1/03-metrics.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/09-design-v1/03-metrics.md -------------------------------------------------------------------------------- /docs/09-design-v1/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "V1 设计文档" 3 | } 4 | -------------------------------------------------------------------------------- /docs/10-contributing/01-overview.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/01-overview.md -------------------------------------------------------------------------------- /docs/10-contributing/02-profiling_index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/02-profiling_index.md -------------------------------------------------------------------------------- /docs/10-contributing/03-dockerfile.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/03-dockerfile.md -------------------------------------------------------------------------------- /docs/10-contributing/04-model/01-basic.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/04-model/01-basic.md -------------------------------------------------------------------------------- /docs/10-contributing/04-model/02-registration.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/04-model/02-registration.md -------------------------------------------------------------------------------- /docs/10-contributing/04-model/03-tests.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/04-model/03-tests.md -------------------------------------------------------------------------------- /docs/10-contributing/04-model/04-multimodal.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/04-model/04-multimodal.md -------------------------------------------------------------------------------- /docs/10-contributing/04-model/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/04-model/README.md -------------------------------------------------------------------------------- /docs/10-contributing/05-vulnerability_management.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/10-contributing/05-vulnerability_management.md -------------------------------------------------------------------------------- /docs/10-contributing/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "开发者指南" 3 | } 4 | -------------------------------------------------------------------------------- /docs/11-api/01-offline_interence/01-llm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/01-offline_interence/01-llm.md -------------------------------------------------------------------------------- /docs/11-api/01-offline_interence/02-llm_inputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/01-offline_interence/02-llm_inputs.md -------------------------------------------------------------------------------- /docs/11-api/01-offline_interence/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/01-offline_interence/README.md -------------------------------------------------------------------------------- /docs/11-api/02-engine/01-llm_engine.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/02-engine/01-llm_engine.md -------------------------------------------------------------------------------- /docs/11-api/02-engine/02-async_llm_engine.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/02-engine/02-async_llm_engine.md -------------------------------------------------------------------------------- /docs/11-api/02-engine/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/02-engine/README.md -------------------------------------------------------------------------------- /docs/11-api/03-inference_params.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/03-inference_params.md -------------------------------------------------------------------------------- /docs/11-api/04-multimodal/01-inputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/04-multimodal/01-inputs.md -------------------------------------------------------------------------------- /docs/11-api/04-multimodal/02-parse.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/04-multimodal/02-parse.md -------------------------------------------------------------------------------- /docs/11-api/04-multimodal/03-processing.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/04-multimodal/03-processing.md -------------------------------------------------------------------------------- /docs/11-api/04-multimodal/04-profiling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/04-multimodal/04-profiling.md -------------------------------------------------------------------------------- /docs/11-api/04-multimodal/05-registry.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/04-multimodal/05-registry.md -------------------------------------------------------------------------------- /docs/11-api/04-multimodal/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/04-multimodal/README.md -------------------------------------------------------------------------------- /docs/11-api/05-model/01-interfaces_base.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/05-model/01-interfaces_base.md -------------------------------------------------------------------------------- /docs/11-api/05-model/02-interfaces.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/05-model/02-interfaces.md -------------------------------------------------------------------------------- /docs/11-api/05-model/03-adapters.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/11-api/05-model/03-adapters.md -------------------------------------------------------------------------------- /docs/11-api/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "API" 3 | } 4 | -------------------------------------------------------------------------------- /docs/12-community/01-blog.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/12-community/01-blog.md -------------------------------------------------------------------------------- /docs/12-community/02-meetups.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/12-community/02-meetups.md -------------------------------------------------------------------------------- /docs/12-community/03-sponsors.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/12-community/03-sponsors.md -------------------------------------------------------------------------------- /docs/12-community/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "社区" 3 | } 4 | -------------------------------------------------------------------------------- /docs/13-vllm-tutorials/01-vLLM-stepbysteb.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/13-vllm-tutorials/01-vLLM-stepbysteb.md -------------------------------------------------------------------------------- /docs/13-vllm-tutorials/02-infer-34b-with-vllm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/13-vllm-tutorials/02-infer-34b-with-vllm.md -------------------------------------------------------------------------------- /docs/13-vllm-tutorials/03-few-shot-w-qwen2-5.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/13-vllm-tutorials/03-few-shot-w-qwen2-5.md -------------------------------------------------------------------------------- /docs/13-vllm-tutorials/04-vllm-langchain-tutorial.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/13-vllm-tutorials/04-vllm-langchain-tutorial.md -------------------------------------------------------------------------------- /docs/13-vllm-tutorials/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "vLLM 教程" 3 | } 4 | -------------------------------------------------------------------------------- /docs/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docs/index.md -------------------------------------------------------------------------------- /docusaurus.config.ts: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/docusaurus.config.ts -------------------------------------------------------------------------------- /nginx.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/nginx.conf -------------------------------------------------------------------------------- /package.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/package.json -------------------------------------------------------------------------------- /pnpm-lock.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/pnpm-lock.yaml -------------------------------------------------------------------------------- /sidebars.ts: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/sidebars.ts -------------------------------------------------------------------------------- /src/components/HomepageFeatures/index.tsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/components/HomepageFeatures/index.tsx -------------------------------------------------------------------------------- /src/components/HomepageFeatures/styles.module.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/components/HomepageFeatures/styles.module.css -------------------------------------------------------------------------------- /src/css/custom.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/css/custom.css -------------------------------------------------------------------------------- /src/pages/about.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/pages/about.md -------------------------------------------------------------------------------- /src/pages/index.module.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/pages/index.module.css -------------------------------------------------------------------------------- /src/pages/index.tsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/pages/index.tsx -------------------------------------------------------------------------------- /src/pages/markdown-page.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/src/pages/markdown-page.md -------------------------------------------------------------------------------- /static/.nojekyll: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /static/img/1-High-efficiency.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/1-High-efficiency.svg -------------------------------------------------------------------------------- /static/img/2Memory-Management.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/2Memory-Management.svg -------------------------------------------------------------------------------- /static/img/3-Flexible-user-friendly.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/3-Flexible-user-friendly.svg -------------------------------------------------------------------------------- /static/img/docs/02-07/01-Deploying&scaling-up-with-SkyPilot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-07/01-Deploying&scaling-up-with-SkyPilot.png -------------------------------------------------------------------------------- /static/img/docs/02-07/05-Deploying-with-Cerebrium.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-07/05-Deploying-with-Cerebrium.png -------------------------------------------------------------------------------- /static/img/docs/02-07/07-Deploying-with-dstack.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-07/07-Deploying-with-dstack.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/api_path.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/api_path.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/bangding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/bangding.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/curl_res.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/curl_res.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/curl_res_local.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/curl_res_local.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/id.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/id.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/model.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/res_api.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/res_api.png -------------------------------------------------------------------------------- /static/img/docs/02-tutorials/start.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/02-tutorials/start.png -------------------------------------------------------------------------------- /static/img/docs/07-03/Overview_of_the_step.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-03/Overview_of_the_step.png -------------------------------------------------------------------------------- /static/img/docs/07-04/k_vecs.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/k_vecs.png -------------------------------------------------------------------------------- /static/img/docs/07-04/key.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/key.png -------------------------------------------------------------------------------- /static/img/docs/07-04/logits_vec.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/logits_vec.png -------------------------------------------------------------------------------- /static/img/docs/07-04/q_vecs.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/q_vecs.png -------------------------------------------------------------------------------- /static/img/docs/07-04/query.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/query.png -------------------------------------------------------------------------------- /static/img/docs/07-04/v_vec.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/v_vec.png -------------------------------------------------------------------------------- /static/img/docs/07-04/value.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-04/value.png -------------------------------------------------------------------------------- /static/img/docs/07-07/dockerfile-stages-dependency.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/07-07/dockerfile-stages-dependency.png -------------------------------------------------------------------------------- /static/img/docs/v1-API/01-llm_engine_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-API/01-llm_engine_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-Developer_Guide/02-profiling_index_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-Developer_Guide/02-profiling_index_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-Developer_Guide/03-dockerfile_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-Developer_Guide/03-dockerfile_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-deployment/02-cerebrium_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-deployment/02-cerebrium_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-deployment/03-dstack_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-deployment/03-dstack_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-deployment/04-helm_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-deployment/04-helm_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-deployment/07-skypilot_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-deployment/07-skypilot_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/01-arch_overview_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/01-arch_overview_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/01-arch_overview_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/01-arch_overview_2.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/01-arch_overview_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/01-arch_overview_3.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_2.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_3.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_4.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_5.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_5.jpg -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_6.png -------------------------------------------------------------------------------- /static/img/docs/v1-design/04-paged_attention_7.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design/04-paged_attention_7.jpg -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_2.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_3.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_4.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_5.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_6.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_7.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/02-prefix_caching_8.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/02-prefix_caching_8.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/03-metrics_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/03-metrics_1.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/03-metrics_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/03-metrics_2.png -------------------------------------------------------------------------------- /static/img/docs/v1-design_v1/03-metrics_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-design_v1/03-metrics_3.png -------------------------------------------------------------------------------- /static/img/docs/v1-features/07-disagg_prefill_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-features/07-disagg_prefill_1.jpg -------------------------------------------------------------------------------- /static/img/docs/v1-features/07-disagg_prefill_2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docs/v1-features/07-disagg_prefill_2.jpg -------------------------------------------------------------------------------- /static/img/docusaurus-social-card.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docusaurus-social-card.jpg -------------------------------------------------------------------------------- /static/img/docusaurus.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/docusaurus.png -------------------------------------------------------------------------------- /static/img/favicon.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/favicon.ico -------------------------------------------------------------------------------- /static/img/logo.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/logo.svg -------------------------------------------------------------------------------- /static/img/undraw_docusaurus_mountain.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/undraw_docusaurus_mountain.svg -------------------------------------------------------------------------------- /static/img/undraw_docusaurus_react.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/undraw_docusaurus_react.svg -------------------------------------------------------------------------------- /static/img/undraw_docusaurus_tree.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/undraw_docusaurus_tree.svg -------------------------------------------------------------------------------- /static/img/vllm-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/static/img/vllm-logo.png -------------------------------------------------------------------------------- /tsconfig.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/tsconfig.json -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/01-installation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/01-installation.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/02-installation-with-rocm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/02-installation-with-rocm.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/03-installation-with-openvino.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/03-installation-with-openvino.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/04-installation-with-cpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/04-installation-with-cpu.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/05-installation-with-neuron.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/05-installation-with-neuron.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/06-installation-with-tpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/06-installation-with-tpu.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/07-installation-with-xpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/07-installation-with-xpu.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/08-quickstart.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/08-quickstart.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/09-debugging-tips.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/09-debugging-tips.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/10-examples.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/10-examples.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/01-api_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/01-api_client.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/02-aqlm_example.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/02-aqlm_example.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/03-cpu_offload.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/03-cpu_offload.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/04-gguf_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/04-gguf_inference.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/05-gradio_openai_chatbot_webserver.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/05-gradio_openai_chatbot_webserver.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/06-gradio_webserver.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/06-gradio_webserver.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/07-llm_engine_example.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/07-llm_engine_example.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/08-lora_with_quantization_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/08-lora_with_quantization_inference.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/09-multilora_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/09-multilora_inference.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/10-offline_chat_with_tools.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/10-offline_chat_with_tools.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/11-offline_inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/11-offline_inference.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/12-offline_inference_arctic.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/12-offline_inference_arctic.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/13-offline_inference_audio_language.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/13-offline_inference_audio_language.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/14-offline_inference_chat.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/14-offline_inference_chat.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/15-offline_inference_distributed.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/15-offline_inference_distributed.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/16-offline_inference_embedding.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/16-offline_inference_embedding.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/17-offline_inference_encoder_decoder.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/17-offline_inference_encoder_decoder.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/18-offline_inference_mlpspeculator.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/18-offline_inference_mlpspeculator.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/19-offline_inference_neuron.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/19-offline_inference_neuron.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/20-offline_inference_neuron_int8_quantization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/20-offline_inference_neuron_int8_quantization.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/21-offline_inference_pixtral.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/21-offline_inference_pixtral.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/22-offline_inference_tpu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/22-offline_inference_tpu.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/23-offline_inference_vision_language.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/23-offline_inference_vision_language.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/24-offline_inference_vision_language_multi_image.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/24-offline_inference_vision_language_multi_image.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/25-offline_inference_with_prefix.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/25-offline_inference_with_prefix.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/26-offline_inference_with_profiler.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/26-offline_inference_with_profiler.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/27-openai_audio_api_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/27-openai_audio_api_client.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/28-openai_chat_completion_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/28-openai_chat_completion_client.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/29-openai_chat_completion_client_with_tools.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/29-openai_chat_completion_client_with_tools.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/30-openai_completion_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/30-openai_completion_client.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/31-openai_embedding_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/31-openai_embedding_client.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/32-openai_vision_api_client.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/32-openai_vision_api_client.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/33-save_sharded_state.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/33-save_sharded_state.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/34-tensorize_vllm_model.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/01-getting-started/10-examples/examples/34-tensorize_vllm_model.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/01-getting-started/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "快速开始" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/01-openai-compatible-server.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/01-openai-compatible-server.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/02-deploying-with-docker.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/02-deploying-with-docker.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/03-distributed-inference-and-serving.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/03-distributed-inference-and-serving.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/04-production-metrics.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/04-production-metrics.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/05-environment-variables.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/05-environment-variables.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/06-usage-stats-collection.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/06-usage-stats-collection.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/01-deploying&scaling-up-with-skypilot.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/01-deploying&scaling-up-with-skypilot.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/02-deploying-with-kserve.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/02-deploying-with-kserve.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/03-deploying-with-nvidia-triton.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/03-deploying-with-nvidia-triton.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/04-deploying-with-bentoml.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/04-deploying-with-bentoml.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/05-deploying-with-cerebrium.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/05-deploying-with-cerebrium.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/06-deploying-with-lws.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/06-deploying-with-lws.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/07-deploying-with-dstack.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/07-deploying-with-dstack.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/08-serving-with-langchain.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/08-serving-with-langchain.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/09-serving-with-llama_index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/09-serving-with-llama_index.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/07-integrations/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/07-integrations/readme.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/08-tensorizer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/08-tensorizer.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/09-compatibility matrix.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/09-compatibility matrix.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/10-frequently-asked-questions.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/02-serving/10-frequently-asked-questions.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/02-serving/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "部署" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/01-supported-models.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/01-supported-models.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/02-adding-a-new-model.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/02-adding-a-new-model.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/03-enabling-multimodal-inputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/03-enabling-multimodal-inputs.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/04-engine-arguments.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/04-engine-arguments.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/05-using-lora-adapters.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/05-using-lora-adapters.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/06-using-vlms.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/06-using-vlms.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/07-speculative-decoding-in-vllm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/07-speculative-decoding-in-vllm.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/08-performance-and-tuning.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/03-models/08-performance-and-tuning.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/03-models/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "支持模型" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/01-supported_hardware.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/01-supported_hardware.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/02-autoawq.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/02-autoawq.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/03-bitsandbytes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/03-bitsandbytes.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/04-gguf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/04-gguf.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/05-int8-w8a8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/05-int8-w8a8.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/06-fp8-w8a8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/06-fp8-w8a8.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/07-fp8-e5m2-kv-cache.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/07-fp8-e5m2-kv-cache.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/08-fp8-e4m3-kv-cache.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/04-quantization/08-fp8-e4m3-kv-cache.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/04-quantization/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "量化" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/05-automatic-prefix-caching/01-introduction-apc.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/05-automatic-prefix-caching/01-introduction-apc.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/05-automatic-prefix-caching/02-implementation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/05-automatic-prefix-caching/02-implementation.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/05-automatic-prefix-caching/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "自动前缀缓存" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/06-performance-benchmarks/06-benchmark-suites-of-vllm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/06-performance-benchmarks/06-benchmark-suites-of-vllm.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/06-performance-benchmarks/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "性能基准测试" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/01-sampling-parameters.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/01-sampling-parameters.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/02-offline-inference/01-llm-class.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/02-offline-inference/01-llm-class.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/02-offline-inference/02-llm-inputs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/02-offline-inference/02-llm-inputs.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/02-offline-inference/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/02-offline-inference/readme.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/03-vllm-engine/01-llmengine.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/03-vllm-engine/01-llmengine.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/03-vllm-engine/02-asyncllmengine.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/03-vllm-engine/02-asyncllmengine.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/03-vllm-engine/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/03-vllm-engine/readme.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/04-vllm-paged-attention.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/04-vllm-paged-attention.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/05-input-processing/01-model_inputs_index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/05-input-processing/01-model_inputs_index.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/05-input-processing/02-input-processing-pipeline.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/05-input-processing/02-input-processing-pipeline.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/05-input-processing/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "输入处理" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/06-multi-modality/01-adding-a-multimodal-plugin.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/06-multi-modality/01-adding-a-multimodal-plugin.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/06-multi-modality/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/06-multi-modality/readme.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/07-dockerfile.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/07-dockerfile.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/08-profiling-vllm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/07-developer-documentation/08-profiling-vllm.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/07-developer-documentation/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "开发者文档" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/08-indices-and-tables/01-index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/08-indices-and-tables/01-index.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/08-indices-and-tables/02-python-module-index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/08-indices-and-tables/02-python-module-index.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/08-indices-and-tables/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "索引与表" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/09-community/01-vllm-meetups.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/09-community/01-vllm-meetups.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/09-community/02-sponsors.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/09-community/02-sponsors.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/09-community/_category_.json: -------------------------------------------------------------------------------- 1 | { 2 | "label": "社区" 3 | } 4 | -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/10-tutorials/01-vLLM-stepbysteb.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/10-tutorials/01-vLLM-stepbysteb.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/10-tutorials/02-infer-34b-with-vllm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/10-tutorials/02-infer-34b-with-vllm.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/10-tutorials/03-few-shot-w-qwen2-5.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/10-tutorials/03-few-shot-w-qwen2-5.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/10-tutorials/04-vllm-langchain-tutorial.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/10-tutorials/04-vllm-langchain-tutorial.md -------------------------------------------------------------------------------- /versioned_docs/version-0.8.x/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_docs/version-0.8.x/index.md -------------------------------------------------------------------------------- /versioned_sidebars/version-0.8.x-sidebars.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hyperai/vllm-cn/HEAD/versioned_sidebars/version-0.8.x-sidebars.json -------------------------------------------------------------------------------- /versions.json: -------------------------------------------------------------------------------- 1 | [ 2 | "0.8.x" 3 | ] 4 | --------------------------------------------------------------------------------