ee804ce23e
### What this PR does / why we need it?
Upgrade vllm commit to 0318.
Main content: Added a pre-operation for cleaning up and waiting(default
max 50s) for the completion of the clean up of the NPU memory to some
test cases that failed due to the failure to release the NPU memory in a
timely manner when the previous test cases were executed.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
NA
- vLLM version: v0.17.0
- vLLM main:
4497431df6
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
47 lines
1.6 KiB
Docker
47 lines
1.6 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 ascendai/python:3.11-ubuntu22.04
|
|
|
|
ARG TARGETARCH
|
|
|
|
RUN apt-get update -y && \
|
|
apt-get install -y curl git gcc g++ cmake libnuma-dev jq && \
|
|
rm -rf /var/cache/apt/* && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
|
|
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
|
|
# For lint purpose, actually we need make a main2main matching.
|
|
ARG VLLM_COMMIT=8b6325758cce5f9c36d38f2462edbd368b97a07c
|
|
RUN git clone $VLLM_REPO /vllm-workspace/vllm && \
|
|
cd /vllm-workspace/vllm && \
|
|
git checkout $VLLM_COMMIT
|
|
|
|
# # Install vLLM common dependencies
|
|
RUN python3 -m pip install -r /vllm-workspace/vllm/requirements/common.txt --extra-index https://download.pytorch.org/whl/cpu/ && \
|
|
python3 -m pip uninstall -y triton && \
|
|
python3 -m pip cache purge
|
|
|
|
COPY . /vllm-workspace/vllm-ascend/
|
|
|
|
RUN pip install -r /vllm-workspace/vllm-ascend/requirements-dev.txt --extra-index-url https://download.pytorch.org/whl/cpu && \
|
|
pip cache purge && \
|
|
rm -fr /vllm-workspace/
|
|
|
|
CMD ["/bin/bash"]
|