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

[CI]Cleanup accurary test (#4861)

Browse Source 
### What this PR does / why we need it?
Delete accuracy testing of some models:
- Qwen2-VL-7B-Instruct
- Qwen2.5-VL-7B-Instruct
- gemma-2-9b-it
- DeepSeek-V2-Lite

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2025-12-10 14:13:56 +08:00
committed by GitHub
parent e32014ac1d
commit 7132ae8532
6 changed files with 0 additions and 53 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

@@ -82,7 +82,6 @@ jobs:
- os: linux-aarch64-a2-1
model_list:
- Qwen3-8B
- Qwen2.5-VL-7B-Instruct
- Qwen2-Audio-7B-Instruct
- Qwen3-8B-W8A8
- Qwen3-VL-8B-Instruct
@@ -91,7 +90,6 @@ jobs:
- os: linux-aarch64-a2-1
model_list:
- ERNIE-4.5-21B-A3B-PT
- gemma-2-9b-it
- gemma-3-4b-it
- internlm-7b
- InternVL3_5-8B-hf
@@ -101,7 +99,6 @@ jobs:
model_list:
- Qwen3-30B-A3B
- Qwen3-VL-30B-A3B-Instruct
- DeepSeek-V2-Lite
- Qwen3-30B-A3B-W8A8
- os: linux-aarch64-a2-4
model_list: