Skip to content

GitLab

Unverified Commit 7bb736d0 authored by ZiTian Zhao's avatar ZiTian Zhao Committed by GitHub
Browse files

Fix Qwen2.5 VL image grid docstring (#27033) 


Signed-off-by: default avatarzitian zhao <zitian.zhao@tencentmusic.com>
parent 9f4e3090
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/models/qwen2_5_vl.py
View file @ 7bb736d0
...@@ -116,7 +116,7 @@ class Qwen2_5_VLImagePixelInputs(TensorSchema): ...@@ -116,7 +116,7 @@ class Qwen2_5_VLImagePixelInputs(TensorSchema):
- pixel_values shape: (num_patches, num_channels * patch_size * - pixel_values shape: (num_patches, num_channels * patch_size *
patch_size) patch_size)
- image_grid_thw shape: (num_images, 3) in (grid_t, grid_h, grid_w) - image_grid_thw shape: (num_images, 3) in (grid_t, grid_h, grid_w)
formatnum_channels * patch_size * patch_size format.
""" """
type: Literal["pixel_values"] type: Literal["pixel_values"]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment