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

[CI] Add Qwen3-0.6B-Base test (#717)

Browse Source 
### What this PR does / why we need it?
Add Qwen3-0.6B-Base for integration test

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-04-29 14:35:19 +08:00
committed by GitHub
parent 0dae55a9a3
commit d6be63e11d
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/singlecard/test_offline_inference.py
View File

@@ -32,6 +32,7 @@ from tests.conftest import VllmRunner
MODELS = [ MODELS = [
"Qwen/Qwen2.5-0.5B-Instruct", "Qwen/Qwen2.5-0.5B-Instruct",
"vllm-ascend/Qwen2.5-0.5B-Instruct-w8a8", "vllm-ascend/Qwen2.5-0.5B-Instruct-w8a8",
"Qwen/Qwen3-0.6B-Base",
] ]
MULTIMODALITY_MODELS = ["Qwen/Qwen2.5-VL-3B-Instruct"] MULTIMODALITY_MODELS = ["Qwen/Qwen2.5-VL-3B-Instruct"]
os.environ["VLLM_USE_MODELSCOPE"] = "True" os.environ["VLLM_USE_MODELSCOPE"] = "True"