Files
xc-llm-ascend/.github/Dockerfile.buildwheel
zzzzwwjj 1fd56b1106 chip type judgement code optimization (#4485)
### What this PR does / why we need it?
| | cpu envir | npu envir |
|---|---|---|
| set `SOC_VERSION` | check if `SOC_VERSION` is in dict `soc_to_device`,
if not, raise an error that can not support current chip type. | print a
warning log when `SOC_VERSION` is not equal to chip type from `npu-smi`,
same as left for others. |
| not set `SOC_VERSION` | raise an error that `SOC_VERSION` is necessary
when compiling in a cpu envir. | use chip type from `npu-smi` to compile
vllm-ascend. |

### Does this PR introduce _any_ user-facing change?

Now we must set env `SOC_VERSION` when compiling in cpu envir. 

### How was this patch tested?


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

Signed-off-by: zzzzwwjj <1183291235@qq.com>
2025-11-27 17:18:49 +08:00

48 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.
#
ARG PY_VERSION=3.11
FROM quay.io/ascend/manylinux:8.3.rc1-910b-manylinux_2_28-py${PY_VERSION}
ARG COMPILE_CUSTOM_KERNELS=1
ARG SOC_VERSION
# Define environments
ENV DEBIAN_FRONTEND=noninteractive
ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
ENV SOC_VERSION=$SOC_VERSION
RUN yum update -y && \
yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
rm -rf /var/cache/yum
WORKDIR /workspace
COPY . /workspace/vllm-ascend/
# Install req
RUN python3 -m pip install -r vllm-ascend/requirements.txt --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip install twine
# Install vllm-ascend
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
cd vllm-ascend && \
python3 setup.py bdist_wheel && \
ls -l dist
CMD ["/bin/bash"]