huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-19 22:02:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Moving those deps directly into pyproject.

Browse Source
This commit is contained in:
Nicolas Patry 2025-02-06 19:55:39 +01:00
parent 1e5d27a256
commit 98c1496ea6
No known key found for this signature in database
GPG Key ID: 690EBED7128A9DC8
2 changed files with 26 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
Dockerfile_intel
View File

@ -105,23 +105,16 @@ COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1 ENV UV_SYSTEM_PYTHON=1
RUN cd server && \ RUN cd server && \
pip install -U pip uv && \ pip install -U pip uv && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --no-install-project && \ uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --extra intel-xpu --no-install-project && \
. ./.venv/bin/activate && \ . ./.venv/bin/activate && \
make gen-server-raw make gen-server-raw
RUN cd server && \ RUN cd server && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines && \ uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --extra intel-xpu && \
. ./.venv/bin/activate && \ . ./.venv/bin/activate && \
pwd && \ pwd && \
text-generation-server --help text-generation-server --help
RUN . ./server/.venv/bin/activate && pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torch-2.5.0a0%2Bgite84e33f-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN . ./server/.venv/bin/activate && pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torchaudio-2.5.0a0%2B56bc006-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN . ./server/.venv/bin/activate && pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torchvision-0.20.0a0%2B8e8a208-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN . ./server/.venv/bin/activate && pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/oneccl_bind_pt-2.5.0%2Bxpu-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN . ./server/.venv/bin/activate pip install triton-xpu==3.0.0b2 --no-cache-dir
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib
ENV CCL_ZE_IPC_EXCHANGE=sockets ENV CCL_ZE_IPC_EXCHANGE=sockets
#ENV TORCH_LLM_ALLREDUCE=1 #ENV TORCH_LLM_ALLREDUCE=1
@ -194,12 +187,6 @@ RUN case ${TARGETPLATFORM} in \
RUN conda install -c conda-forge gperftools mkl RUN conda install -c conda-forge gperftools mkl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.5.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.20.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install triton==3.1.0 py-libnuma
WORKDIR /usr/src WORKDIR /usr/src
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout b7b552baf64283b594665b8687430fe92990e497 RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout b7b552baf64283b594665b8687430fe92990e497
@ -224,12 +211,12 @@ COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1 ENV UV_SYSTEM_PYTHON=1
RUN cd server && \ RUN cd server && \
pip install -U pip uv && \ pip install -U pip uv && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --no-install-project && \ uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --extra intel-cpu --no-install-project && \
. ./.venv/bin/activate && \ . ./.venv/bin/activate && \
make gen-server-raw make gen-server-raw
RUN cd server && \ RUN cd server && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines && \ uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --extra intel-cpu && \
. ./.venv/bin/activate && \ . ./.venv/bin/activate && \
pwd && \ pwd && \
text-generation-server --help text-generation-server --help

22
server/pyproject.toml
View File

@ -67,6 +67,21 @@ gen = [
"grpcio-tools>=1.69.0", "grpcio-tools>=1.69.0",
"mypy-protobuf>=3.6.0", "mypy-protobuf>=3.6.0",
] ]
intel-xpu = [
"torch-intel-xpu",
"torchaudio-intel-xpu",
"torchvision-intel-xpu",
"oneccl-intel-xpu",
"triton-xpu==3.0.0b2"
]
intel-cpu = [
"torch-intel-cpu",
"torchaudio-intel-cpu",
"torchvision-intel-cpu",
"oneccl-intel-cpu",
"triton==3.1.0",
"py-libnuma"
]
[tool.uv.sources] [tool.uv.sources]
attention-kernels.url = "https://github.com/danieldk/attention-kernels/releases/download/v0.2.0.post2/attention_kernels-0.2.0.post2+cu123torch2.5-cp39-abi3-linux_x86_64.whl" attention-kernels.url = "https://github.com/danieldk/attention-kernels/releases/download/v0.2.0.post2/attention_kernels-0.2.0.post2+cu123torch2.5-cp39-abi3-linux_x86_64.whl"
@ -77,6 +92,13 @@ marlin-kernels = [
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl", marker = "python_version == '3.12'" }, { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl", marker = "python_version == '3.12'" },
] ]
moe-kernels.url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl" moe-kernels.url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl"
torch-intel-xpu.url = "https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torch-2.5.0a0%2Bgite84e33f-cp311-cp311-linux_x86_64.whl"
torchaudio-intel-xpu.url = "https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torchaudio-2.5.0a0%2B56bc006-cp311-cp311-linux_x86_64.whl"
torchvision-intel-xpu.url = "https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torchvision-0.20.0a0%2B8e8a208-cp311-cp311-linux_x86_64.whl"
oneccl-intel-xpu.url = "https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/oneccl_bind_pt-2.5.0%2Bxpu-cp311-cp311-linux_x86_64.whl"
torch-intel-cpu.url = "https://download.pytorch.org/whl/nightly/cpu/torch-2.5.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl"
torchaudio-intel-cpu.url = "https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl"
torchvision-intel-cpu.url = "https://download.pytorch.org/whl/nightly/cpu/torchvision-0.20.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl"
[tool.pytest.ini_options] [tool.pytest.ini_options]
markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"] markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"]