20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Bugfix for PixtralHF models without spatial_merge_size (#16513)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-04-11 17:32:22 -06:00 committed by GitHub
parent 56c76c2e0e
commit 87b836ba77
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/models/pixtral.py
View File

@ -926,8 +926,9 @@ class PixtralHFEncoderInfo(VisionEncoderInfo[PixtralVisionConfig]):
return self.vision_config.image_size
def get_patch_size(self) -> int:
return (self.vision_config.patch_size *
self.vision_config.spatial_merge_size)
spatial_merge_size = getattr(self.vision_config, "spatial_merge_size",
1)
return (self.vision_config.patch_size * spatial_merge_size)
def get_patch_grid_length(self) -> int:
image_size, patch_size = self.get_image_size(), self.get_patch_size()