A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Fix Qwen2.5 VL image grid docstring (#27033)
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com>
ZiTian Zhao committed
Oct 17, 2025 at 00:57 UTC
7bb736d00e81c6cd893007323641dd974d921715
1 file changed
+1
-1
vllm/model_executor/models/qwen2_5_vl.py
+1
-1
@@ -116,7 +116,7 @@ class Qwen2_5_VLImagePixelInputs(TensorSchema):
116
- pixel_values shape: (num_patches, num_channels * patch_size *
117
patch_size)
118
- image_grid_thw shape: (num_images, 3) in (grid_t, grid_h, grid_w)
119
- formatnum_channels * patch_size * patch_size
119
+ format.
120
"""
121
122
type: Literal["pixel_values"]