biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Fix Qwen25VL packed_modules_mapping (#23604)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Jee Jee Li
2025-08-26 16:09:14 +08:00
committed by GitHub
parent ff77764f86
commit 9b5f64238f
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/models/qwen2_5_vl.py
View File

@@ -853,6 +853,7 @@ class Qwen2_5_VLForConditionalGeneration(nn.Module, SupportsMultiModal,
SupportsQuant): SupportsQuant):
packed_modules_mapping = { packed_modules_mapping = {
"qkv_proj": ["q_proj", "k_proj", "v_proj"],
"gate_up_proj": ["gate_proj", "up_proj"], "gate_up_proj": ["gate_proj", "up_proj"],
} }