EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix GLM45v launch server cuda torch compile bug (#9554)

Browse Source
This commit is contained in:
Binyao Jiang
2025-08-25 13:46:28 -07:00
committed by GitHub
parent 3affa9dcc3
commit 24a8cee66d
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
python/sglang/srt/models/qwen2_5_vl.py
View File

@@ -526,6 +526,7 @@ class Qwen2_5_VLForConditionalGeneration(nn.Module):
def get_input_embeddings(self): def get_input_embeddings(self):
return self.model.embed_tokens return self.model.embed_tokens
@torch.no_grad()
def forward( def forward(
self, self,
input_ids: torch.Tensor, input_ids: torch.Tensor,