bc69d7cfe1
Bump vLLM version to v0.11.2 What's broken and changed by vLLM: 1. structured_output is broken by https://github.com/vllm-project/vllm/pull/26866 2. get_mrope_input_positions is broken by https://github.com/vllm-project/vllm/pull/28399 3. graph mode is broken by https://github.com/vllm-project/vllm/pull/25110 we'll upgrade torch to 2.8 to fix the problem later 4. embedding is broken by https://github.com/vllm-project/vllm/pull/27583 5. `get_attn_backend_cls` and attention backend is broken are broken by https://github.com/vllm-project/vllm/pull/28534 6. spec decode is broken by https://github.com/vllm-project/vllm/pull/28771 7. sp feature is broken by https://github.com/vllm-project/vllm/pull/27126 8. mtp is broken by https://github.com/vllm-project/vllm/pull/27922 9. lora is broken by https://github.com/vllm-project/vllm/pull/21068 10. execute_model is broken by https://github.com/vllm-project/vllm/pull/26866 11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by https://github.com/vllm-project/vllm/pull/28159 12. kv cahe is broken by https://github.com/vllm-project/vllm/pull/27753 13. dp is broken by https://github.com/vllm-project/vllm/pull/25110 What's broken and changed by ourself: 1. qwen vl is broken by https://github.com/vllm-project/vllm/pull/28455 We'll remove model files in the future to avoid this kind of error 2. Engine core is broken by https://github.com/vllm-project/vllm/pull/23691 We'll remove the patch file in the future. 3. Ascend scheduler is broken by https://github.com/vllm-project/vllm/pull/28733 We'll remove ascend scheudler later. 4. qwen3-next is broken by https://github.com/vllm-project/vllm/pull/28083 We'll remove model files in the future to avoid this kind of error 5. qwen vl is broken by https://github.com/vllm-project/vllm/pull/27764. We'll remove model files in the future Known issue: 1. ray doesn't work 2. the accuracy of qwen3-next is not correct 3. qwen3-vl is broken 4. prefix cache+ ascend scheduler + deepseek v2 lite is broken. Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Co-authored-by: 22dimensions <waitingwind@foxmail.com> Co-authored-by: shen-shanshan <467638484@qq.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com>
72 lines
3.2 KiB
Docker
72 lines
3.2 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:8.3.rc1-a3-openeuler24.03-py3.11
|
|
|
|
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
|
|
ARG COMPILE_CUSTOM_KERNELS=1
|
|
ARG MOONCAKE_TAG="v0.3.7.post2"
|
|
|
|
ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
|
|
|
|
RUN pip config set global.index-url ${PIP_INDEX_URL}
|
|
|
|
WORKDIR /workspace
|
|
|
|
COPY . /vllm-workspace/vllm-ascend/
|
|
|
|
SHELL ["/bin/bash", "-c"]
|
|
|
|
RUN yum update -y && \
|
|
yum install -y git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
|
|
git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
|
|
cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
|
|
ARCH=$(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:$LD_LIBRARY_PATH && \
|
|
export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/c++/12:/usr/include/c++/12/${ARCH}-openEuler-linux && \
|
|
cd /vllm-workspace/Mooncake && \
|
|
bash mooncake_installer.sh -y && \
|
|
mkdir -p build && cd build && cmake .. -DUSE_ASCEND_DIRECT=ON && \
|
|
make -j$(nproc) && make install && \
|
|
rm -fr /vllm-workspace/Mooncake/build && \
|
|
rm -rf /var/cache/yum/*
|
|
|
|
# Install vLLM
|
|
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
|
|
ARG VLLM_TAG=v0.11.2
|
|
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
|
|
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
|
|
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
|
|
python3 -m pip uninstall -y triton && \
|
|
python3 -m pip cache purge
|
|
|
|
# Install vllm-ascend
|
|
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
|
|
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
|
|
source /usr/local/Ascend/nnal/atb/set_env.sh && \
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
|
|
export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/c++/12:/usr/include/c++/12/`uname -i`-openEuler-linux && \
|
|
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>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
|
|
python3 -m pip cache purge
|
|
|
|
CMD ["/bin/bash"]
|