[ci][gh200] dockerfile clean up (#11351)
Signed-off-by: drikster80 <ed.sealing@gmail.com> Signed-off-by: youkaichao <youkaichao@gmail.com> Co-authored-by: drikster80 <ed.sealing@gmail.com> Co-authored-by: cenzhiyao <2523403608@qq.com>
This commit is contained in:
co-authored by
drikster80
cenzhiyao
parent
48edab8041
commit
7801f56ed7
+20
-19
@@ -45,17 +45,21 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
|
||||
WORKDIR /workspace
|
||||
|
||||
# install build and runtime dependencies
|
||||
COPY requirements-common.txt requirements-common.txt
|
||||
COPY requirements-cuda.txt requirements-cuda.txt
|
||||
COPY requirements-cuda-arm64.txt requirements-cuda-arm64.txt
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
python3 -m pip install -r requirements-cuda.txt
|
||||
|
||||
# arm64 (GH200) build follows the practice of "use existing pytorch" build,
|
||||
# we need to install torch and torchvision from the nightly builds first,
|
||||
# pytorch will not appear as a vLLM dependency in all of the following steps
|
||||
# after this step
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
|
||||
python3 -m pip install -r requirements-cuda-arm64.txt; \
|
||||
python3 -m pip install --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215"; \
|
||||
fi
|
||||
|
||||
COPY requirements-common.txt requirements-common.txt
|
||||
COPY requirements-cuda.txt requirements-cuda.txt
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
python3 -m pip install -r requirements-cuda.txt
|
||||
|
||||
# cuda arch list used by torch
|
||||
# can be useful for both `dev` and `test`
|
||||
# explicitly set the list to avoid issues with torch 2.2
|
||||
@@ -77,11 +81,6 @@ COPY requirements-build.txt requirements-build.txt
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
python3 -m pip install -r requirements-build.txt
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
|
||||
python3 -m pip install -r requirements-cuda-arm64.txt; \
|
||||
fi
|
||||
|
||||
COPY . .
|
||||
ARG GIT_REPO_CHECK=0
|
||||
RUN --mount=type=bind,source=.git,target=.git \
|
||||
@@ -157,8 +156,6 @@ WORKDIR /vllm-workspace
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ARG TARGETPLATFORM
|
||||
|
||||
COPY requirements-cuda-arm64.txt requirements-cuda-arm64.txt
|
||||
|
||||
RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
|
||||
echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment
|
||||
|
||||
@@ -183,17 +180,20 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
|
||||
# or future versions of triton.
|
||||
RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
|
||||
|
||||
# arm64 (GH200) build follows the practice of "use existing pytorch" build,
|
||||
# we need to install torch and torchvision from the nightly builds first,
|
||||
# pytorch will not appear as a vLLM dependency in all of the following steps
|
||||
# after this step
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
|
||||
python3 -m pip install --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215"; \
|
||||
fi
|
||||
|
||||
# Install vllm wheel first, so that torch etc will be installed.
|
||||
RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
|
||||
--mount=type=cache,target=/root/.cache/pip \
|
||||
python3 -m pip install dist/*.whl --verbose
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
|
||||
pip uninstall -y torch && \
|
||||
python3 -m pip install -r requirements-cuda-arm64.txt; \
|
||||
fi
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
. /etc/environment && \
|
||||
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
|
||||
@@ -244,6 +244,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
else \
|
||||
pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' 'timm==0.9.10'; \
|
||||
fi
|
||||
|
||||
ENV VLLM_USAGE_SOURCE production-docker-image
|
||||
|
||||
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
|
||||
|
||||
Reference in New Issue
Block a user