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 4, 17:30 UTC
Fix Nano Nemotron VL static image inputs (#40724)
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
milesial committed
Apr 24, 2026 at 02:18 UTC
9ad5abe7722ba4eb9cb484689dd90529e76c41c5
1 file changed
+3
-1
vllm/model_executor/models/nano_nemotron_vl.py
+3
-1
@@ -1124,7 +1124,9 @@ class NemotronH_Nano_VL_V2(
1124
)
1125
else:
1126
return NanoNemotronVLImagePixelInputs(
1127
- num_patches=kwargs.pop("image_num_patches"), **kwargs
1127
+ pixel_values_flat=pixel_values_flat,
1128
+ num_patches=kwargs.pop("image_num_patches"),
1129
+ **kwargs,
1130
)
1131
1132
def _process_image_input_dynamic(