iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Model] Add Qwen4Exp to the Qwen GDN Triton warmup (#56742)

Browse Source 
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
This commit is contained in:
SeongJun Lee
2026-10-02 21:38:15 +08:00
committed by GitHub
co-authored by lesj0610 Claude Opus 5 Thien Tran
parent 30e956fad3
commit 24df2d3fc7
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/model_executor/warmup/qwen_triton_warmup.py
+2
View File
@@ -22,6 +22,8 @@ _QWEN_MODEL_TYPES = frozenset(
"qwen3_5_text",
"qwen3_5_moe",
"qwen3_5_moe_text",
"qwen4_exp",
"qwen4_exp_text",
}
)