chore: bump v0.3.6.post3 (#2259)
This commit is contained in:
@@ -23,31 +23,32 @@ RUN pip3 install datamodel_code_generator
|
||||
|
||||
WORKDIR /sgl-workspace
|
||||
|
||||
ARG CUDA_VERSION
|
||||
RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \
|
||||
&& git clone --depth=1 https://github.com/sgl-project/sglang.git \
|
||||
&& cd sglang \
|
||||
&& if [ "$BUILD_TYPE" = "srt" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]"; \
|
||||
if [ "$CUDA_VERSION" = "12.1.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu121/torch2.4/flashinfer/; \
|
||||
elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/; \
|
||||
elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu118/torch2.4/flashinfer/; \
|
||||
else \
|
||||
echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
|
||||
fi; \
|
||||
else \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]"; \
|
||||
if [ "$CUDA_VERSION" = "12.1.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.4/flashinfer/; \
|
||||
elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/; \
|
||||
elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu118/torch2.4/flashinfer/; \
|
||||
else \
|
||||
echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
|
||||
fi; \
|
||||
fi
|
||||
|
||||
ARG CUDA_VERSION
|
||||
RUN if [ "$CUDA_VERSION" = "12.1.1" ]; then \
|
||||
export CUDA_IDENTIFIER=cu121 && \
|
||||
python3 -m pip --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/; \
|
||||
elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
|
||||
export CUDA_IDENTIFIER=cu124 && \
|
||||
python3 -m pip --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu124/torch2.4/; \
|
||||
elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
|
||||
export CUDA_IDENTIFIER=cu118 && \
|
||||
python3 -m pip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu118 && \
|
||||
python3 -m pip --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu118/torch2.4/; \
|
||||
else \
|
||||
echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
|
||||
fi
|
||||
|
||||
RUN python3 -m pip cache purge
|
||||
|
||||
|
||||
ENV DEBIAN_FRONTEND=interactive
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
# Usage (to build SGLang ROCm docker image):
|
||||
# docker build --build-arg SGL_BRANCH=v0.3.6.post2 -t v0.3.6.post2-rocm620 -f Dockerfile.rocm .
|
||||
# docker build --build-arg SGL_BRANCH=v0.3.6.post3 -t v0.3.6.post3-rocm620 -f Dockerfile.rocm .
|
||||
|
||||
# default base image
|
||||
ARG BASE_IMAGE="rocm/vllm-dev:20241022"
|
||||
|
||||
Reference in New Issue
Block a user