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 7, 12:45 UTC
Fix typo: implictly -> implicitly in isaac.py docstring (#35646)
lin-shh committed
Mar 1, 2026 at 02:34 UTC
a9ec392c86446996087e6919eaf59023c984b8fe
1 file changed
+1
-1
vllm/model_executor/models/isaac.py
+1
-1
@@ -551,7 +551,7 @@ def process_vision_for_patches(
551
`(num_images, height, width, channels)` for a batch. Channels are
552
expected to be RGB.
553
patch_size (`int`):
554
- Edge length of square patches; implictly controls resize grid granularity.
554
+ Edge length of square patches; implicitly controls resize grid granularity.
555
max_num_patches (`int`):
556
Maximum number of patches allowed after resizing.
557
min_num_patches (`int`, *optional*):