[Test] Refactor accuracy test to nightly test (#3814)

### What this PR does / why we need it?
Refactor accuracy test to nightly test

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2025-11-06 09:06:59 +08:00
committed by GitHub
parent b1488ecdb1
commit 737cad2b6b
4 changed files with 142 additions and 146 deletions

View File

@@ -27,6 +27,7 @@ on:
pull_request:
branches:
- 'main'
types: [ labeled, synchronize ]
# Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly
# declared as "shell: bash -el {0}" on steps that need to be properly activated.
@@ -88,3 +89,44 @@ jobs:
config_file_path: ${{ matrix.test_config.config_file_path }}
secrets:
KUBECONFIG_B64: ${{ secrets.KUBECONFIG_A2_B64 }}
single-node-accuracy-tests:
if: >-
${{
github.event_name == 'schedule' ||
github.event_name == 'workflow_dispatch' ||
(
contains(github.event.pull_request.labels.*.name, 'accuracy-test') &&
contains(github.event.pull_request.labels.*.name, 'ready-for-test')
)
}}
strategy:
fail-fast: false
matrix:
test_config:
- os: linux-aarch64-a2-1
model_list:
- Qwen3-8B
- Qwen2.5-VL-7B-Instruct
# TODO: This model has a bug that needs to be fixed and readded
# - Qwen2-Audio-7B-Instruct
- Qwen3-8B-W8A8
- Qwen3-VL-8B-Instruct
- Qwen2.5-Omni-7B
- Meta-Llama-3.1-8B-Instruct
- os: linux-aarch64-a2-2
model_list:
- Qwen3-30B-A3B
- Qwen3-VL-30B-A3B-Instruct
- DeepSeek-V2-Lite
- Qwen3-30B-A3B-W8A8
- os: linux-aarch64-a2-4
model_list:
- Qwen3-Next-80B-A3B-Instruct
uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
with:
vllm: v0.11.0
runner: ${{ matrix.test_config.os }}
model_list: ${{ toJson(matrix.test_config.model_list) }}
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
upload: false