feat: Add SageMaker support (#3740)
This commit is contained in:
Andrew Smith
78
docker/Dockerfile.sagemaker
Normal file
78
docker/Dockerfile.sagemaker
Normal file
@@ -0,0 +1,78 @@
|
||||
ARG CUDA_VERSION=12.5.1
|
||||
|
||||
FROM nvcr.io/nvidia/tritonserver:24.04-py3-min
|
||||
|
||||
ARG BUILD_TYPE=all
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
|
||||
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
|
||||
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
|
||||
&& apt update -y \
|
||||
&& apt install software-properties-common -y \
|
||||
&& add-apt-repository ppa:deadsnakes/ppa -y && apt update \
|
||||
&& apt install python3.10 python3.10-dev -y \
|
||||
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1 \
|
||||
&& update-alternatives --set python3 /usr/bin/python3.10 && apt install python3.10-distutils -y \
|
||||
&& apt install curl git sudo libibverbs-dev -y \
|
||||
&& apt install -y rdma-core infiniband-diags openssh-server perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 \
|
||||
&& curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python3 get-pip.py \
|
||||
&& python3 --version \
|
||||
&& python3 -m pip --version \
|
||||
&& rm -rf /var/lib/apt/lists/* \
|
||||
&& apt clean
|
||||
|
||||
# For openbmb/MiniCPM models
|
||||
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 \
|
||||
&& if [ "$CUDA_VERSION" = "12.1.1" ]; then \
|
||||
python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu121; \
|
||||
elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
|
||||
python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu124; \
|
||||
elif [ "$CUDA_VERSION" = "12.5.1" ]; then \
|
||||
python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu124; \
|
||||
elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
|
||||
python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu118; \
|
||||
python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
|
||||
else \
|
||||
echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
|
||||
fi \
|
||||
&& cd sglang \
|
||||
&& if [ "$BUILD_TYPE" = "srt" ]; then \
|
||||
if [ "$CUDA_VERSION" = "12.1.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu121/torch2.5/flashinfer-python; \
|
||||
elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
|
||||
elif [ "$CUDA_VERSION" = "12.5.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
|
||||
elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu118/torch2.5/flashinfer-python; \
|
||||
python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
|
||||
else \
|
||||
echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
|
||||
fi; \
|
||||
else \
|
||||
if [ "$CUDA_VERSION" = "12.1.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.5/flashinfer-python; \
|
||||
elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
|
||||
elif [ "$CUDA_VERSION" = "12.5.1" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
|
||||
elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
|
||||
python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu118/torch2.5/flashinfer-python; \
|
||||
python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
|
||||
else \
|
||||
echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
|
||||
fi; \
|
||||
fi
|
||||
|
||||
ENV DEBIAN_FRONTEND=interactive
|
||||
|
||||
COPY serve /usr/bin/serve
|
||||
RUN chmod 777 /usr/bin/serve
|
||||
|
||||
ENTRYPOINT [ "/usr/bin/serve" ]
|
||||
31
docker/serve
Executable file
31
docker/serve
Executable file
@@ -0,0 +1,31 @@
|
||||
#!/bin/bash
|
||||
|
||||
echo "Starting server"
|
||||
|
||||
SERVER_ARGS="--host 0.0.0.0 --port 8080"
|
||||
|
||||
if [ -n "$TENSOR_PARALLEL_DEGREE" ]; then
|
||||
SERVER_ARGS="${SERVER_ARGS} --tp-size ${TENSOR_PARALLEL_DEGREE}"
|
||||
fi
|
||||
|
||||
if [ -n "$DATA_PARALLEL_DEGREE" ]; then
|
||||
SERVER_ARGS="${SERVER_ARGS} --dp-size ${DATA_PARALLEL_DEGREE}"
|
||||
fi
|
||||
|
||||
if [ -n "$EXPERT_PARALLEL_DEGREE" ]; then
|
||||
SERVER_ARGS="${SERVER_ARGS} --ep-size ${EXPERT_PARALLEL_DEGREE}"
|
||||
fi
|
||||
|
||||
if [ -n "$MEM_FRACTION_STATIC" ]; then
|
||||
SERVER_ARGS="${SERVER_ARGS} --mem-fraction-static ${MEM_FRACTION_STATIC}"
|
||||
fi
|
||||
|
||||
if [ -n "$QUANTIZATION" ]; then
|
||||
SERVER_ARGS="${SERVER_ARGS} --quantization ${QUANTIZATION}"
|
||||
fi
|
||||
|
||||
if [ -n "$CHUNKED_PREFILL_SIZE" ]; then
|
||||
SERVER_ARGS="${SERVER_ARGS} --chunked-prefill-size ${CHUNKED_PREFILL_SIZE}"
|
||||
fi
|
||||
|
||||
python3 -m sglang.launch_server --model-path /opt/ml/model $SERVER_ARGS
|
||||
Reference in New Issue
Block a user