EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Fix] fix Qwen2-Audio-7B-Instruct accuracy test (#4017)

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

fix Qwen2-Audio-7B-Instruct accuracy test

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

### How was this patch tested?

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

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2025-11-10 11:54:18 +08:00
committed by GitHub
parent de49fb3deb
commit d40ba52454
3 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/vllm_ascend_test_nightly_a2.yaml vendored
View File

@@ -108,8 +108,7 @@ jobs:
model_list: model_list:
- Qwen3-8B - Qwen3-8B
- Qwen2.5-VL-7B-Instruct - Qwen2.5-VL-7B-Instruct
# TODO: This model has a bug that needs to be fixed and readded - Qwen2-Audio-7B-Instruct
# - Qwen2-Audio-7B-Instruct
- Qwen3-8B-W8A8 - Qwen3-8B-W8A8
- Qwen3-VL-8B-Instruct - Qwen3-VL-8B-Instruct
- Qwen2.5-Omni-7B - Qwen2.5-Omni-7B

3
.github/workflows/vllm_ascend_test_report.yaml vendored
View File

@@ -64,8 +64,7 @@ jobs:
model_list: model_list:
- Qwen3-8B - Qwen3-8B
- Qwen2.5-VL-7B-Instruct - Qwen2.5-VL-7B-Instruct
# TODO: This model has a bug that needs to be fixed and readded - Qwen2-Audio-7B-Instruct
# - Qwen2-Audio-7B-Instruct
- runner: linux-aarch64-a2-2 - runner: linux-aarch64-a2-2
model_list: model_list:
- Qwen3-30B-A3B - Qwen3-30B-A3B

1
tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml
View File

@@ -8,3 +8,4 @@ tasks:
- name: "exact_match,flexible-extract" - name: "exact_match,flexible-extract"
value: 0.45 value: 0.45
num_fewshot: 5 num_fewshot: 5
gpu_memory_utilization: 0.8