├── .gitignore ├── BlueLM_technical_report.pdf ├── CHANGELOG.md ├── MODEL_LICENSE.pdf ├── MODEL_LICENSE_EN.pdf ├── OpenAtom Model License.pdf ├── README.md ├── README_EN.md ├── cli_demo.py ├── cli_demo_tool.py ├── example ├── vllm │ ├── .github │ │ └── workflows │ │ │ ├── publish.yml │ │ │ ├── pylint.yml │ │ │ ├── scripts │ │ │ ├── build.sh │ │ │ ├── create_release.js │ │ │ ├── cuda-install.sh │ │ │ ├── env.sh │ │ │ └── pytorch-install.sh │ │ │ └── yapf.yml │ ├── .gitignore │ ├── .pylintrc │ ├── .readthedocs.yaml │ ├── CONTRIBUTING.md │ ├── Dockerfile │ ├── LICENSE │ ├── MANIFEST.in │ ├── README.md │ ├── benchmarks │ │ ├── README.md │ │ ├── benchmark_latency.py │ │ ├── benchmark_serving.py │ │ ├── benchmark_throughput.py │ │ ├── kernels │ │ │ └── benchmark_paged_attention.py │ │ └── launch_tgi_server.sh │ ├── csrc │ │ ├── activation.cpp │ │ ├── activation_kernels.cu │ │ ├── attention.cpp │ │ ├── attention │ │ │ ├── attention_dtypes.h │ │ │ ├── attention_generic.cuh │ │ │ ├── attention_kernels.cu │ │ │ ├── attention_utils.cuh │ │ │ ├── dtype_bfloat16.cuh │ │ │ ├── dtype_float16.cuh │ │ │ └── dtype_float32.cuh │ │ ├── cache.cpp │ │ ├── cache_kernels.cu │ │ ├── cuda_utils.cpp │ │ ├── cuda_utils_kernels.cu │ │ ├── dispatch_utils.h │ │ ├── layernorm.cpp │ │ ├── layernorm_kernels.cu │ │ ├── pos_encoding.cpp │ │ ├── pos_encoding_kernels.cu │ │ ├── quantization.cpp │ │ ├── quantization │ │ │ ├── awq │ │ │ │ ├── dequantize.cuh │ │ │ │ └── gemm_kernels.cu │ │ │ └── squeezellm │ │ │ │ └── quant_cuda_kernel.cu │ │ └── reduction_utils.cuh │ ├── docs │ │ ├── Makefile │ │ ├── README.md │ │ ├── make.bat │ │ ├── requirements-docs.txt │ │ └── source │ │ │ ├── assets │ │ │ └── logos │ │ │ │ ├── vllm-logo-only-light.png │ │ │ │ ├── vllm-logo-text-dark.png │ │ │ │ └── vllm-logo-text-light.png │ │ │ ├── conf.py │ │ │ ├── getting_started │ │ │ ├── installation.rst │ │ │ └── quickstart.rst │ │ │ ├── index.rst │ │ │ ├── models │ │ │ ├── adding_model.rst │ │ │ └── supported_models.rst │ │ │ ├── quantization │ │ │ └── auto_awq.rst │ │ │ └── serving │ │ │ ├── deploying_with_docker.rst │ │ │ ├── deploying_with_triton.rst │ │ │ ├── distributed_serving.rst │ │ │ └── run_on_sky.rst │ ├── examples │ │ ├── api_client.py │ │ ├── gradio_webserver.py │ │ ├── llm_engine_example.py │ │ ├── offline_inference.py │ │ ├── openai_chatcompletion_client.py │ │ └── openai_completion_client.py │ ├── format.sh │ ├── mypy.ini │ ├── pyproject.toml │ ├── requirements-dev.txt │ ├── requirements.txt │ ├── setup.py │ ├── tests │ │ ├── __init__.py │ │ ├── async_engine │ │ │ ├── api_server_async_engine.py │ │ │ ├── test_api_server.py │ │ │ ├── test_async_llm_engine.py │ │ │ └── test_request_tracker.py │ │ ├── conftest.py │ │ ├── distributed │ │ │ └── test_comm_ops.py │ │ ├── engine │ │ │ └── test_detokenize.py │ │ ├── kernels │ │ │ ├── conftest.py │ │ │ ├── test_activation.py │ │ │ ├── test_attention.py │ │ │ ├── test_cache.py │ │ │ ├── test_layernorm.py │ │ │ └── test_pos_encoding.py │ │ ├── models │ │ │ └── test_models.py │ │ ├── samplers │ │ │ ├── test_beam_search.py │ │ │ ├── test_logprobs.py │ │ │ └── test_sampler.py │ │ └── worker │ │ │ └── test_worker.py │ └── vllm │ │ ├── __init__.py │ │ ├── block.py │ │ ├── config.py │ │ ├── core │ │ ├── __init__.py │ │ ├── block_manager.py │ │ ├── policy.py │ │ └── scheduler.py │ │ ├── engine │ │ ├── __init__.py │ │ ├── arg_utils.py │ │ ├── async_llm_engine.py │ │ ├── llm_engine.py │ │ └── ray_utils.py │ │ ├── entrypoints │ │ ├── __init__.py │ │ ├── api_server.py │ │ ├── llm.py │ │ └── openai │ │ │ ├── __init__.py │ │ │ ├── api_server.py │ │ │ └── protocol.py │ │ ├── logger.py │ │ ├── model_executor │ │ ├── __init__.py │ │ ├── input_metadata.py │ │ ├── layers │ │ │ ├── __init__.py │ │ │ ├── activation.py │ │ │ ├── attention.py │ │ │ ├── layernorm.py │ │ │ ├── linear.py │ │ │ ├── quantization │ │ │ │ ├── __init__.py │ │ │ │ ├── awq.py │ │ │ │ ├── base_config.py │ │ │ │ └── squeezellm.py │ │ │ ├── rotary_embedding.py │ │ │ ├── sampler.py │ │ │ └── vocab_parallel_embedding.py │ │ ├── model_loader.py │ │ ├── models │ │ │ ├── __init__.py │ │ │ ├── aquila.py │ │ │ ├── baichuan.py │ │ │ ├── bloom.py │ │ │ ├── bluelm.py │ │ │ ├── chatglm.py │ │ │ ├── falcon.py │ │ │ ├── gpt2.py │ │ │ ├── gpt_bigcode.py │ │ │ ├── gpt_j.py │ │ │ ├── gpt_neox.py │ │ │ ├── internlm.py │ │ │ ├── llama.py │ │ │ ├── mistral.py │ │ │ ├── mpt.py │ │ │ ├── opt.py │ │ │ ├── qwen.py │ │ │ └── yi.py │ │ ├── parallel_utils │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── communication_op.py │ │ │ ├── parallel_state.py │ │ │ └── utils.py │ │ ├── utils.py │ │ └── weight_utils.py │ │ ├── outputs.py │ │ ├── py.typed │ │ ├── sampling_params.py │ │ ├── sequence.py │ │ ├── transformers_utils │ │ ├── __init__.py │ │ ├── config.py │ │ ├── configs │ │ │ ├── __init__.py │ │ │ ├── aquila.py │ │ │ ├── baichuan.py │ │ │ ├── bluelm.py │ │ │ ├── chatglm.py │ │ │ ├── falcon.py │ │ │ ├── qwen.py │ │ │ └── yi.py │ │ └── tokenizer.py │ │ ├── utils.py │ │ └── worker │ │ ├── __init__.py │ │ ├── cache_engine.py │ │ └── worker.py └── vllm_demo.py ├── openai_api_demo ├── api_server.py └── openai_api_request.py ├── quant_cuda ├── quant_cuda.cpp ├── quant_cuda_kernel.cu └── setup_cuda.py ├── requirements.txt ├── resources ├── cli_demo.gif ├── web_demo.gif └── wechat.png ├── train ├── data │ ├── bella_dev_demo.json │ └── bella_train_demo.json ├── lora_inference.py ├── main.py ├── script │ ├── bluelm-7b-sft-lora.sh │ ├── bluelm-7b-sft.sh │ └── bluelm-7b.sh └── utils │ ├── dataloader.py │ ├── ds_utils.py │ ├── finetune_peft.py │ ├── sampler.py │ └── utils.py └── web_demo.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/.gitignore -------------------------------------------------------------------------------- /BlueLM_technical_report.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/BlueLM_technical_report.pdf -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/CHANGELOG.md -------------------------------------------------------------------------------- /MODEL_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/MODEL_LICENSE.pdf -------------------------------------------------------------------------------- /MODEL_LICENSE_EN.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/MODEL_LICENSE_EN.pdf -------------------------------------------------------------------------------- /OpenAtom Model License.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/OpenAtom Model License.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/README.md -------------------------------------------------------------------------------- /README_EN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/README_EN.md -------------------------------------------------------------------------------- /cli_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/cli_demo.py -------------------------------------------------------------------------------- /cli_demo_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/cli_demo_tool.py -------------------------------------------------------------------------------- /example/vllm/.github/workflows/publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/publish.yml -------------------------------------------------------------------------------- /example/vllm/.github/workflows/pylint.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/pylint.yml -------------------------------------------------------------------------------- /example/vllm/.github/workflows/scripts/build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/scripts/build.sh -------------------------------------------------------------------------------- /example/vllm/.github/workflows/scripts/create_release.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/scripts/create_release.js -------------------------------------------------------------------------------- /example/vllm/.github/workflows/scripts/cuda-install.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/scripts/cuda-install.sh -------------------------------------------------------------------------------- /example/vllm/.github/workflows/scripts/env.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/scripts/env.sh -------------------------------------------------------------------------------- /example/vllm/.github/workflows/scripts/pytorch-install.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/scripts/pytorch-install.sh -------------------------------------------------------------------------------- /example/vllm/.github/workflows/yapf.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.github/workflows/yapf.yml -------------------------------------------------------------------------------- /example/vllm/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.gitignore -------------------------------------------------------------------------------- /example/vllm/.pylintrc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.pylintrc -------------------------------------------------------------------------------- /example/vllm/.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/.readthedocs.yaml -------------------------------------------------------------------------------- /example/vllm/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/CONTRIBUTING.md -------------------------------------------------------------------------------- /example/vllm/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/Dockerfile -------------------------------------------------------------------------------- /example/vllm/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/LICENSE -------------------------------------------------------------------------------- /example/vllm/MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/MANIFEST.in -------------------------------------------------------------------------------- /example/vllm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/README.md -------------------------------------------------------------------------------- /example/vllm/benchmarks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/benchmarks/README.md -------------------------------------------------------------------------------- /example/vllm/benchmarks/benchmark_latency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/benchmarks/benchmark_latency.py -------------------------------------------------------------------------------- /example/vllm/benchmarks/benchmark_serving.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/benchmarks/benchmark_serving.py -------------------------------------------------------------------------------- /example/vllm/benchmarks/benchmark_throughput.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/benchmarks/benchmark_throughput.py -------------------------------------------------------------------------------- /example/vllm/benchmarks/kernels/benchmark_paged_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/benchmarks/kernels/benchmark_paged_attention.py -------------------------------------------------------------------------------- /example/vllm/benchmarks/launch_tgi_server.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/benchmarks/launch_tgi_server.sh -------------------------------------------------------------------------------- /example/vllm/csrc/activation.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/activation.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/activation_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/activation_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/attention.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/attention/attention_dtypes.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/attention_dtypes.h -------------------------------------------------------------------------------- /example/vllm/csrc/attention/attention_generic.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/attention_generic.cuh -------------------------------------------------------------------------------- /example/vllm/csrc/attention/attention_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/attention_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/attention/attention_utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/attention_utils.cuh -------------------------------------------------------------------------------- /example/vllm/csrc/attention/dtype_bfloat16.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/dtype_bfloat16.cuh -------------------------------------------------------------------------------- /example/vllm/csrc/attention/dtype_float16.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/dtype_float16.cuh -------------------------------------------------------------------------------- /example/vllm/csrc/attention/dtype_float32.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/attention/dtype_float32.cuh -------------------------------------------------------------------------------- /example/vllm/csrc/cache.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/cache.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/cache_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/cache_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/cuda_utils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/cuda_utils.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/cuda_utils_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/cuda_utils_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/dispatch_utils.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/dispatch_utils.h -------------------------------------------------------------------------------- /example/vllm/csrc/layernorm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/layernorm.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/layernorm_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/layernorm_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/pos_encoding.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/pos_encoding.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/pos_encoding_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/pos_encoding_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/quantization.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/quantization.cpp -------------------------------------------------------------------------------- /example/vllm/csrc/quantization/awq/dequantize.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/quantization/awq/dequantize.cuh -------------------------------------------------------------------------------- /example/vllm/csrc/quantization/awq/gemm_kernels.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/quantization/awq/gemm_kernels.cu -------------------------------------------------------------------------------- /example/vllm/csrc/quantization/squeezellm/quant_cuda_kernel.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/quantization/squeezellm/quant_cuda_kernel.cu -------------------------------------------------------------------------------- /example/vllm/csrc/reduction_utils.cuh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/csrc/reduction_utils.cuh -------------------------------------------------------------------------------- /example/vllm/docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/Makefile -------------------------------------------------------------------------------- /example/vllm/docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/README.md -------------------------------------------------------------------------------- /example/vllm/docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/make.bat -------------------------------------------------------------------------------- /example/vllm/docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/requirements-docs.txt -------------------------------------------------------------------------------- /example/vllm/docs/source/assets/logos/vllm-logo-only-light.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/assets/logos/vllm-logo-only-light.png -------------------------------------------------------------------------------- /example/vllm/docs/source/assets/logos/vllm-logo-text-dark.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/assets/logos/vllm-logo-text-dark.png -------------------------------------------------------------------------------- /example/vllm/docs/source/assets/logos/vllm-logo-text-light.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/assets/logos/vllm-logo-text-light.png -------------------------------------------------------------------------------- /example/vllm/docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/conf.py -------------------------------------------------------------------------------- /example/vllm/docs/source/getting_started/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/getting_started/installation.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/getting_started/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/getting_started/quickstart.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/index.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/models/adding_model.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/models/adding_model.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/models/supported_models.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/models/supported_models.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/quantization/auto_awq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/quantization/auto_awq.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/serving/deploying_with_docker.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/serving/deploying_with_docker.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/serving/deploying_with_triton.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/serving/deploying_with_triton.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/serving/distributed_serving.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/serving/distributed_serving.rst -------------------------------------------------------------------------------- /example/vllm/docs/source/serving/run_on_sky.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/docs/source/serving/run_on_sky.rst -------------------------------------------------------------------------------- /example/vllm/examples/api_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/examples/api_client.py -------------------------------------------------------------------------------- /example/vllm/examples/gradio_webserver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/examples/gradio_webserver.py -------------------------------------------------------------------------------- /example/vllm/examples/llm_engine_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/examples/llm_engine_example.py -------------------------------------------------------------------------------- /example/vllm/examples/offline_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/examples/offline_inference.py -------------------------------------------------------------------------------- /example/vllm/examples/openai_chatcompletion_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/examples/openai_chatcompletion_client.py -------------------------------------------------------------------------------- /example/vllm/examples/openai_completion_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/examples/openai_completion_client.py -------------------------------------------------------------------------------- /example/vllm/format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/format.sh -------------------------------------------------------------------------------- /example/vllm/mypy.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/mypy.ini -------------------------------------------------------------------------------- /example/vllm/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/pyproject.toml -------------------------------------------------------------------------------- /example/vllm/requirements-dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/requirements-dev.txt -------------------------------------------------------------------------------- /example/vllm/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/requirements.txt -------------------------------------------------------------------------------- /example/vllm/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/setup.py -------------------------------------------------------------------------------- /example/vllm/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/tests/async_engine/api_server_async_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/async_engine/api_server_async_engine.py -------------------------------------------------------------------------------- /example/vllm/tests/async_engine/test_api_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/async_engine/test_api_server.py -------------------------------------------------------------------------------- /example/vllm/tests/async_engine/test_async_llm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/async_engine/test_async_llm_engine.py -------------------------------------------------------------------------------- /example/vllm/tests/async_engine/test_request_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/async_engine/test_request_tracker.py -------------------------------------------------------------------------------- /example/vllm/tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/conftest.py -------------------------------------------------------------------------------- /example/vllm/tests/distributed/test_comm_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/distributed/test_comm_ops.py -------------------------------------------------------------------------------- /example/vllm/tests/engine/test_detokenize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/engine/test_detokenize.py -------------------------------------------------------------------------------- /example/vllm/tests/kernels/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/kernels/conftest.py -------------------------------------------------------------------------------- /example/vllm/tests/kernels/test_activation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/kernels/test_activation.py -------------------------------------------------------------------------------- /example/vllm/tests/kernels/test_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/kernels/test_attention.py -------------------------------------------------------------------------------- /example/vllm/tests/kernels/test_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/kernels/test_cache.py -------------------------------------------------------------------------------- /example/vllm/tests/kernels/test_layernorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/kernels/test_layernorm.py -------------------------------------------------------------------------------- /example/vllm/tests/kernels/test_pos_encoding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/kernels/test_pos_encoding.py -------------------------------------------------------------------------------- /example/vllm/tests/models/test_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/models/test_models.py -------------------------------------------------------------------------------- /example/vllm/tests/samplers/test_beam_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/samplers/test_beam_search.py -------------------------------------------------------------------------------- /example/vllm/tests/samplers/test_logprobs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/samplers/test_logprobs.py -------------------------------------------------------------------------------- /example/vllm/tests/samplers/test_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/samplers/test_sampler.py -------------------------------------------------------------------------------- /example/vllm/tests/worker/test_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/tests/worker/test_worker.py -------------------------------------------------------------------------------- /example/vllm/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/__init__.py -------------------------------------------------------------------------------- /example/vllm/vllm/block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/block.py -------------------------------------------------------------------------------- /example/vllm/vllm/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/config.py -------------------------------------------------------------------------------- /example/vllm/vllm/core/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/core/block_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/core/block_manager.py -------------------------------------------------------------------------------- /example/vllm/vllm/core/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/core/policy.py -------------------------------------------------------------------------------- /example/vllm/vllm/core/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/core/scheduler.py -------------------------------------------------------------------------------- /example/vllm/vllm/engine/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/engine/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/engine/arg_utils.py -------------------------------------------------------------------------------- /example/vllm/vllm/engine/async_llm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/engine/async_llm_engine.py -------------------------------------------------------------------------------- /example/vllm/vllm/engine/llm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/engine/llm_engine.py -------------------------------------------------------------------------------- /example/vllm/vllm/engine/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/engine/ray_utils.py -------------------------------------------------------------------------------- /example/vllm/vllm/entrypoints/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/entrypoints/api_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/entrypoints/api_server.py -------------------------------------------------------------------------------- /example/vllm/vllm/entrypoints/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/entrypoints/llm.py -------------------------------------------------------------------------------- /example/vllm/vllm/entrypoints/openai/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/entrypoints/openai/api_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/entrypoints/openai/api_server.py -------------------------------------------------------------------------------- /example/vllm/vllm/entrypoints/openai/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/entrypoints/openai/protocol.py -------------------------------------------------------------------------------- /example/vllm/vllm/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/logger.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/__init__.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/input_metadata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/input_metadata.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/activation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/activation.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/attention.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/layernorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/layernorm.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/linear.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/quantization/__init__.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/quantization/awq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/quantization/awq.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/quantization/base_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/quantization/base_config.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/quantization/squeezellm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/quantization/squeezellm.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/rotary_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/rotary_embedding.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/sampler.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/layers/vocab_parallel_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/layers/vocab_parallel_embedding.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/model_loader.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/__init__.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/aquila.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/aquila.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/baichuan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/baichuan.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/bloom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/bloom.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/bluelm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/bluelm.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/chatglm.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/falcon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/falcon.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/gpt2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/gpt2.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/gpt_bigcode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/gpt_bigcode.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/gpt_j.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/gpt_j.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/gpt_neox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/gpt_neox.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/internlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/internlm.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/llama.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/mistral.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/mpt.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/opt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/opt.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/qwen.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/models/yi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/models/yi.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/parallel_utils/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/parallel_utils/README.md -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/parallel_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/parallel_utils/communication_op.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/parallel_utils/communication_op.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/parallel_utils/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/parallel_utils/parallel_state.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/parallel_utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/parallel_utils/utils.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/utils.py -------------------------------------------------------------------------------- /example/vllm/vllm/model_executor/weight_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/model_executor/weight_utils.py -------------------------------------------------------------------------------- /example/vllm/vllm/outputs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/outputs.py -------------------------------------------------------------------------------- /example/vllm/vllm/py.typed: -------------------------------------------------------------------------------- 1 | # Marker file for PEP 561. 2 | # The vllm package uses inline types. 3 | -------------------------------------------------------------------------------- /example/vllm/vllm/sampling_params.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/sampling_params.py -------------------------------------------------------------------------------- /example/vllm/vllm/sequence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/sequence.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/config.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/__init__.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/aquila.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/aquila.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/baichuan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/baichuan.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/bluelm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/bluelm.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/chatglm.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/falcon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/falcon.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/qwen.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/configs/yi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/configs/yi.py -------------------------------------------------------------------------------- /example/vllm/vllm/transformers_utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/transformers_utils/tokenizer.py -------------------------------------------------------------------------------- /example/vllm/vllm/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/utils.py -------------------------------------------------------------------------------- /example/vllm/vllm/worker/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /example/vllm/vllm/worker/cache_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/worker/cache_engine.py -------------------------------------------------------------------------------- /example/vllm/vllm/worker/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm/vllm/worker/worker.py -------------------------------------------------------------------------------- /example/vllm_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/example/vllm_demo.py -------------------------------------------------------------------------------- /openai_api_demo/api_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/openai_api_demo/api_server.py -------------------------------------------------------------------------------- /openai_api_demo/openai_api_request.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/openai_api_demo/openai_api_request.py -------------------------------------------------------------------------------- /quant_cuda/quant_cuda.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/quant_cuda/quant_cuda.cpp -------------------------------------------------------------------------------- /quant_cuda/quant_cuda_kernel.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/quant_cuda/quant_cuda_kernel.cu -------------------------------------------------------------------------------- /quant_cuda/setup_cuda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/quant_cuda/setup_cuda.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/requirements.txt -------------------------------------------------------------------------------- /resources/cli_demo.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/resources/cli_demo.gif -------------------------------------------------------------------------------- /resources/web_demo.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/resources/web_demo.gif -------------------------------------------------------------------------------- /resources/wechat.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/resources/wechat.png -------------------------------------------------------------------------------- /train/data/bella_dev_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/data/bella_dev_demo.json -------------------------------------------------------------------------------- /train/data/bella_train_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/data/bella_train_demo.json -------------------------------------------------------------------------------- /train/lora_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/lora_inference.py -------------------------------------------------------------------------------- /train/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/main.py -------------------------------------------------------------------------------- /train/script/bluelm-7b-sft-lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/script/bluelm-7b-sft-lora.sh -------------------------------------------------------------------------------- /train/script/bluelm-7b-sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/script/bluelm-7b-sft.sh -------------------------------------------------------------------------------- /train/script/bluelm-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/script/bluelm-7b.sh -------------------------------------------------------------------------------- /train/utils/dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/utils/dataloader.py -------------------------------------------------------------------------------- /train/utils/ds_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/utils/ds_utils.py -------------------------------------------------------------------------------- /train/utils/finetune_peft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/utils/finetune_peft.py -------------------------------------------------------------------------------- /train/utils/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/utils/sampler.py -------------------------------------------------------------------------------- /train/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/train/utils/utils.py -------------------------------------------------------------------------------- /web_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vivo-ai-lab/BlueLM/HEAD/web_demo.py --------------------------------------------------------------------------------