eeedf7c503
### What this PR does / why we need it?
This PR upgrades the vLLM dependency from `v0.14.1` to `v0.15.0`. This
involves:
- Updating the `VLLM_TAG` in all `Dockerfile`.
- Updating the vLLM version in `docs/source/conf.py`.
- Removing conditional code paths specific to `v0.14.1` across the
codebase, which simplifies maintenance.
- Fix `TypeError: MMEncoderAttention.__init__() got an unexpected
keyword argument 'multimodal_config'` due to
https://github.com/vllm-project/vllm/pull/31972.
- Fix `_shared_experts: 'NoneType' object is not callable` due to
https://github.com/vllm-project/vllm/pull/32082 by
https://github.com/vllm-project/vllm-ascend/pull/6335.
- Fix `ReshapeAndCacheOperation setup failed!` due to
https://github.com/vllm-project/vllm/pull/25954 by overriding attention
metadata slots.
This upgrade is necessary to keep the project aligned with the latest
features, bug fixes, and API changes in the vLLM project.
### Does this PR introduce _any_ user-facing change?
No, this is an internal dependency update and does not introduce any
user-facing changes.
### How was this patch tested?
CI is expected to pass with these changes, ensuring that all existing
tests are successful with the new vLLM version.
- vLLM version: v0.14.1
- vLLM main:
dc917cceb8
co-authored-by: shen-shanshan <467638484@qq.com>
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.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=v0.15.0
|
|
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"]
|