922e5c163b
### What this PR does / why we need it? 1. Fix `TypeError: FusedMoEParallelConfig.__init__() missing 1 required positional argument: 'is_sequence_parallel'` due to https://github.com/vllm-project/vllm/pull/32567 2. Fix ` TypeError: '>' not supported between instances of 'MagicMock' and 'int'` due to https://github.com/vllm-project/vllm/pull/33035 3. Fix `TypeError: Can't instantiate abstract class AscendMLAImpl with abstract methods forward_mha, forward_mqa` and AttributeError: 'bool' object has no attribute 'process_weights_after_loading' due to https://github.com/vllm-project/vllm/pull/33284 4. Fix `'AscendSharedFusedMoE' object has no attribute '_routed_input_transform'`due to https://github.com/vllm-project/vllm/pull/32790 5. Fix `NPUModelRunner._dummy_run() got an unexpected keyword argument 'num_active_loras'` due to https://github.com/vllm-project/vllm/pull/32005 6. Fix the problem caused by` 'tuple' object has no attribute 'job_id'` due to https://github.com/vllm-project/vllm/pull/27492 7. Fix the problem that all_moe_layers is not equal to vllm.moe_forward, vllm.moe_forward_shared due to https://github.com/vllm-project/vllm/pull/33184 8. Add patch to fix the problem "got multiple values for keyword argument 'add_special_tokens'" due to https://github.com/vllm-project/vllm/pull/32863 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com> Co-authored-by: hfadzxy <starmoon_zhang@163.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=d7e17aaacd5ed1b4b4be6bcfef3a1b7cbc84fc9a
|
|
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"]
|