[Test] Add e2e test and accuracy test for Qwen3-Next-80B-A3B-Instruct (#3450)

### What this PR does / why we need it?

Add e2e test and accuracy test for Qwen3-Next-80B-A3B-Instruct

### How was this patch tested?
accuracy test:
https://github.com/vllm-project/vllm-ascend/actions/runs/18771221544/job/53556027634?pr=3450
ci test:
https://github.com/vllm-project/vllm-ascend/actions/runs/18771221530/job/53556027614?pr=3450
<img width="1703" height="562" alt="image"
src="https://github.com/user-attachments/assets/973b6cfa-8240-41e3-893a-5024ff8d0693"
/>



- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2025-10-25 10:57:56 +08:00
committed by GitHub
parent d5609e2c48
commit 8f6f967028
5 changed files with 120 additions and 4 deletions

View File

@@ -73,6 +73,16 @@ jobs:
working-directory: ./vllm-empty
run: |
VLLM_TARGET_DEVICE=empty pip install -e .
- name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
if: ${{ inputs.model_name == 'Qwen3-Next-80B-A3B-Instruct' }}
shell: bash -l {0}
run: |
wget -q https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run -O /tmp/Ascend-BiSheng-toolkit_aarch64.run
chmod a+x /tmp/Ascend-BiSheng-toolkit_aarch64.run
/tmp/Ascend-BiSheng-toolkit_aarch64.run --install
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
- name: Resolve vllm-ascend version
run: |