2ecbd8b8bf
Signed-off-by: mywaaagh_admin <pkwarcraft@gmail.com> Signed-off-by: lichaoran <pkwarcraft@gmail.com> Co-authored-by: Even Zhou <even.y.zhou@outlook.com> Co-authored-by: ronnie_zheng <zl19940307@163.com>
82 lines
3.0 KiB
Docker
82 lines
3.0 KiB
Docker
ARG CANN_VERSION=8.2.rc1
|
|
ARG DEVICE_TYPE=a3
|
|
ARG OS=ubuntu22.04
|
|
ARG PYTHON_VERSION=py3.11
|
|
|
|
FROM quay.io/ascend/cann:$CANN_VERSION-$DEVICE_TYPE-$OS-$PYTHON_VERSION
|
|
|
|
# Update pip & apt sources
|
|
ARG PIP_INDEX_URL="https://pypi.org/simple/"
|
|
ARG APTMIRROR=""
|
|
ARG MEMFABRIC_URL=https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/mf_adapter-1.0.0-cp311-cp311-linux_aarch64.whl
|
|
ARG PYTORCH_VERSION=2.6.0
|
|
ARG TORCHVISION_VERSION=0.21.0
|
|
ARG PTA_URL="https://gitee.com/ascend/pytorch/releases/download/v7.1.0.1-pytorch2.6.0/torch_npu-2.6.0.post1-cp311-cp311-manylinux_2_28_aarch64.whl"
|
|
ARG VLLM_TAG=v0.8.5
|
|
ARG TRITON_ASCEND_URL=https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/triton_ascend-3.2.0.dev20250729-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl
|
|
ARG SGLANG_TAG=main
|
|
ARG ASCEND_CANN_PATH=/usr/local/Ascend/ascend-toolkit
|
|
ARG SGLANG_KERNEL_NPU_TAG=main
|
|
|
|
WORKDIR /workspace
|
|
|
|
# Define environments
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
RUN pip config set global.index-url $PIP_INDEX_URL
|
|
RUN if [ -n "$APTMIRROR" ];then sed -i "s|.*.ubuntu.com|$APTMIRROR|g" /etc/apt/sources.list ;fi
|
|
|
|
# Install development tools and utilities
|
|
RUN apt-get update -y && apt upgrade -y && apt-get install -y \
|
|
build-essential \
|
|
cmake \
|
|
vim \
|
|
wget \
|
|
curl \
|
|
net-tools \
|
|
zlib1g-dev \
|
|
lld \
|
|
clang \
|
|
locales \
|
|
ccache \
|
|
ca-certificates \
|
|
&& rm -rf /var/cache/apt/* \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& update-ca-certificates \
|
|
&& locale-gen en_US.UTF-8
|
|
|
|
ENV LANG=en_US.UTF-8
|
|
ENV LANGUAGE=en_US:en
|
|
ENV LC_ALL=en_US.UTF-8
|
|
|
|
# Install dependencies
|
|
# TODO: install from pypi released memfabric
|
|
# TODO: install from pypi released triton-ascend
|
|
RUN pip install $MEMFABRIC_URL --no-cache-dir \
|
|
&& pip install torch==$PYTORCH_VERSION torchvision==$TORCHVISION_VERSION --index-url https://download.pytorch.org/whl/cpu --no-cache-dir \
|
|
&& wget ${PTA_URL} && pip install "./torch_npu-2.6.0.post1-cp311-cp311-manylinux_2_28_aarch64.whl" --no-cache-dir \
|
|
&& pip install ${TRITON_ASCEND_URL} --no-cache-dir \
|
|
&& python3 -m pip install --no-cache-dir numpy==1.26.4 pybind11
|
|
|
|
# Install vLLM
|
|
RUN git clone --depth 1 https://github.com/vllm-project/vllm.git --branch $VLLM_TAG && \
|
|
cd vllm && VLLM_TARGET_DEVICE="empty" pip install -v . --no-cache-dir && \
|
|
cd .. && rm -rf vllm
|
|
|
|
# Install SGLang
|
|
RUN git clone https://github.com/sgl-project/sglang --branch $SGLANG_TAG && \
|
|
cd ./sglang/python && pip install .[srt_npu] --no-cache-dir && \
|
|
cd .. && rm -rf ./sglang
|
|
|
|
# Install Deep-ep
|
|
RUN git clone --branch $SGLANG_KERNEL_NPU_TAG https://github.com/sgl-project/sgl-kernel-npu.git \
|
|
&& export LD_LIBRARY_PATH=${ASCEND_CANN_PATH}/latest/runtime/lib64/stub:$LD_LIBRARY_PATH && \
|
|
source ${ASCEND_CANN_PATH}/set_env.sh && \
|
|
cd sgl-kernel-npu && \
|
|
bash build.sh \
|
|
&& pip install output/deep_ep*.whl --no-cache-dir \
|
|
&& cd .. && rm -rf sgl-kernel-npu \
|
|
&& cd "$(pip show deep-ep | awk '/^Location:/ {print $2}')" && ln -s deep_ep/deep_ep_cpp*.so
|
|
|
|
CMD ["/bin/bash"]
|