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

[Nightly] Use Qwen repo for qwen3-next (#6064)

Browse Source 
### What this PR does / why we need it?
Use Qwen repo for qwen3-next to make nightly test happy. see
https://github.com/vllm-project/vllm-ascend/actions/runs/21179025996/job/60915871441
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
d68209402d

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2026-01-21 10:39:12 +08:00
committed by GitHub
parent 1ed9524763
commit 839e03cbc9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/e2e/nightly/single_node/models/test_qwen3_next.py
View File

@@ -10,7 +10,7 @@ from tests.e2e.conftest import RemoteOpenAIServer
from tools.aisbench import run_aisbench_cases from tools.aisbench import run_aisbench_cases
MODELS = [ MODELS = [
"vllm-ascend/Qwen3-Next-80B-A3B-Instruct", "Qwen/Qwen3-Next-80B-A3B-Instruct",
] ]
MODES = ["aclgraph"] MODES = ["aclgraph"]