Fix wheel glibc version incompatibility (#1582)

### What this PR does / why we need it?
- Fixes https://github.com/vllm-project/vllm-ascend/issues/1533

### How was this patch tested?
1. Run the image
```
docker run \
    --name cann_container \
    --device /dev/davinci6 \
    --device /dev/davinci_manager \
    --device /dev/devmm_svm \
    --device /dev/hisi_hdc \
    -v /usr/local/dcmi:/usr/local/dcmi \
    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
    -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
    -v /etc/ascend_install.info:/etc/ascend_install.info \
    -it  quay.io/ascend/cann:8.1.rc1-910b-openeuler22.03-py3.11 bash
```

2. Install package
torch=2.5.1
torch-npu=2.5.1.post1.dev20250619 
vllm=0.9.1

vllm-ascend=vllm_ascend-0.1.dev1+g02ac443-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl
Artifact download URL:
https://github.com/vllm-project/vllm-ascend/actions/runs/16039661265/artifacts/3454481370

3. Test offline script

```
from vllm import LLM, SamplingParams

import os
os.environ["VLLM_USE_V1"] = "1"

prompts = [
    "Hello, my name is",
]

llm = LLM(model="Qwen3/Qwen3-1.7B")

outputs = llm.generate(prompts)

for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```

4. Results

![result](https://github.com/user-attachments/assets/20f9d923-00ce-4a2d-8598-9b216045705d)

- vLLM version: v0.9.2
- vLLM main:
b942c094e3

---------

Signed-off-by: Icey <1790571317@qq.com>
This commit is contained in:
Icey
2025-07-08 18:46:02 +08:00
committed by GitHub
parent e4e9ea02ab
commit 0d4bc03946
2 changed files with 40 additions and 14 deletions

View File

@@ -15,17 +15,16 @@
# This file is a part of the vllm-ascend project.
#
ARG PY_VERSION=3.10
FROM quay.io/ascend/cann:8.0.0-910b-ubuntu22.04-py${PY_VERSION}
FROM quay.io/ascend/manylinux:8.0.0-910b-manylinux_2_28-py${PY_VERSION}
ARG COMPILE_CUSTOM_KERNELS=1
# Define environments
ENV DEBIAN_FRONTEND=noninteractive
ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
RUN apt-get update -y && \
apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev && \
rm -rf /var/cache/apt/* && \
rm -rf /var/lib/apt/lists/*
RUN yum update -y && \
yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
rm -rf /var/cache/yum
WORKDIR /workspace
@@ -41,8 +40,6 @@ RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
cd vllm-ascend && \
python3 setup.py bdist_wheel && \
ls -l dist && \
for f in dist/*.whl; do mv "$f" "$(echo "$f" | sed -e 's/-linux_x86_64\.whl$/-manylinux1_x86_64.whl/' -e 's/-linux_aarch64\.whl$/-manylinux2014_aarch64.whl/')"; done && \
ls -l dist
ls -l dist
CMD ["/bin/bash"]