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

[Doc] [2/N] Add Fuyu E2E example for multimodal processor (#13331)

Browse Source
This commit is contained in:
Cyrus Leung
2025-02-15 23:06:23 +08:00
committed by GitHub
parent 54ed913f34
commit 367cb8ce8c
2 changed files with 527 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/models/fuyu.py
View File

@@ -104,6 +104,8 @@ class FuyuProcessingInfo(BaseProcessingInfo):
image_processor = self.get_image_processor()
target_width = image_processor.size["width"]
target_height = image_processor.size["height"]
patch_width = image_processor.patch_size["width"]
patch_height = image_processor.patch_size["height"]
if not (image_width <= target_width and image_height <= target_height):
height_scale_factor = target_height / image_height
@@ -113,8 +115,8 @@ class FuyuProcessingInfo(BaseProcessingInfo):
image_height = int(image_height * optimal_scale_factor)
image_width = int(image_width * optimal_scale_factor)
ncols = math.ceil(image_width / 30)
nrows = math.ceil(image_height / 30)
ncols = math.ceil(image_width / patch_width)
nrows = math.ceil(image_height / patch_height)
return ncols, nrows
def get_image_size_with_most_features(self) -> ImageSize: