mirror of
https://github.com/vllm-project/vllm-ascend.git
synced 2025-10-20 13:43:53 +08:00
875a920d4a
### What this PR does / why we need it?
Add support for Ascend A3 and remove latest tag
### Does this PR introduce _any_ user-facing change?
User can run vLLM on Altlas A3 series
### How was this patch tested?
CI passed with:
- remove latest tag test:
https://github.com/wxsIcey/wxs-vllm-ascend/actions/runs/16267635040/job/45926924765
- E2E image build for A3
- CI test on A3 with e2e test and longterm test
- Unit test missing because need a real A3 hardware to have a test
Closes: https://github.com/vllm-project/vllm-ascend/issues/1696
- vLLM version: v0.9.2
- vLLM main:
d0dc4cfca4
---------
Signed-off-by: Icey <1790571317@qq.com>
57 lines
2.2 KiB
Docker
57 lines
2.2 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:8.1.rc1-a3-openeuler22.03-py3.10
|
|
|
|
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
|
|
ARG COMPILE_CUSTOM_KERNELS=1
|
|
|
|
ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
|
|
|
|
RUN yum update -y && \
|
|
yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
|
|
rm -rf /var/cache/yum
|
|
|
|
RUN pip config set global.index-url ${PIP_INDEX_URL}
|
|
|
|
WORKDIR /workspace
|
|
|
|
COPY . /vllm-workspace/vllm-ascend/
|
|
|
|
# Install vLLM
|
|
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
|
|
ARG VLLM_TAG=v0.9.2
|
|
|
|
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
|
|
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
|
|
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
|
|
python3 -m pip uninstall -y triton && \
|
|
python3 -m pip cache purge
|
|
|
|
# Install vllm-ascend
|
|
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
|
|
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
|
|
source /usr/local/Ascend/nnal/atb/set_env.sh && \
|
|
export LD_LIBRARY_PATH=$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 modelscope (for fast download) and ray (for multinode)
|
|
RUN python3 -m pip install modelscope ray && \
|
|
python3 -m pip cache purge
|
|
|
|
CMD ["/bin/bash"] |