986cd45397
### What this PR does / why we need it?
Drop 0.16.0 support in main
- Fix eagle proposer break introduced by
https://github.com/vllm-project/vllm/pull/34552. Mainly change to use
the draft attention group to initialize the attention metadata builder.
- Fix the `ModelRunner` has no attribute `cudagraph_capture_sizes`
error, which is a bug in vLLM v0.17.0, and fixed by a later pr
https://github.com/vllm-project/vllm/pull/30515
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
85 lines
3.7 KiB
Docker
85 lines
3.7 KiB
Docker
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
|
|
FROM quay.io/ascend/cann:8.5.1-910b-ubuntu22.04-py3.11
|
|
|
|
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
|
|
ARG MOONCAKE_TAG="v0.3.8.post1"
|
|
ARG SOC_VERSION="ascend910b1"
|
|
|
|
# Define environments
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
ENV SOC_VERSION=$SOC_VERSION \
|
|
TASK_QUEUE_ENABLE=1 \
|
|
OMP_NUM_THREADS=1
|
|
|
|
WORKDIR /workspace
|
|
|
|
COPY . /vllm-workspace/vllm-ascend/
|
|
|
|
# Install Mooncake dependencies
|
|
RUN apt-get update -y && \
|
|
apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev libjemalloc2 && \
|
|
git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
|
|
cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
|
|
cd /vllm-workspace/Mooncake && bash mooncake_installer.sh -y && \
|
|
ARCH=$(uname -m) && \
|
|
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
|
|
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/${ARCH}-linux/devlib:/usr/local/Ascend/ascend-toolkit/latest/${ARCH}-linux/lib64:$LD_LIBRARY_PATH && \
|
|
mkdir -p build && cd build && cmake .. -DUSE_ASCEND_DIRECT=ON && \
|
|
make -j$(nproc) && make install && \
|
|
rm -fr /vllm-workspace/Mooncake/build && \
|
|
rm -rf /var/cache/apt/* && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
RUN pip config set global.index-url ${PIP_INDEX_URL}
|
|
|
|
# Install vLLM
|
|
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
|
|
ARG VLLM_TAG=v0.17.0
|
|
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
|
|
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
|
|
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
|
|
python3 -m pip uninstall -y triton && \
|
|
python3 -m pip cache purge
|
|
|
|
# Install vllm-ascend
|
|
# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
|
|
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
|
|
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
|
|
source /usr/local/Ascend/nnal/atb/set_env.sh && \
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
|
|
python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
|
|
python3 -m pip cache purge
|
|
|
|
# Install clang-15 (for triton-ascend)
|
|
RUN apt-get update -y && \
|
|
apt-get -y install clang-15 && \
|
|
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20 && \
|
|
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20 && \
|
|
rm -rf /var/cache/apt/* && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install modelscope (for fast download) and ray (for multinode)
|
|
RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
|
|
python3 -m pip cache purge
|
|
|
|
RUN echo "export LD_PRELOAD=/usr/lib/$(uname -m)-linux-gnu/libjemalloc.so.2:$LD_PRELOAD" >> ~/.bashrc
|
|
RUN echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib" >> ~/.bashrc
|
|
|
|
CMD ["/bin/bash"]
|