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
[Bugfix] Fix HF format InternVL large variants video processing (#27330)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Oct 22, 2025 at 23:39 UTC
db6f28d89832326520afecfab4672c7eca8c1147
1 file changed
+4
-1
vllm/model_executor/models/interns1.py
+4
-1
@@ -182,7 +182,10 @@ class InternS1ProcessingInfo(BaseProcessingInfo):
182
def get_hf_processor(self, **kwargs: object) -> InternVLProcessor:
183
hf_processor = self.ctx.get_hf_processor(InternVLProcessor, **kwargs)
184
hf_processor.video_processor = cached_video_processor_from_config(
185
- self.ctx.model_config, processor_cls=InternVLVideoProcessor, **kwargs
185
+ self.ctx.model_config,
186
+ processor_cls=InternVLVideoProcessor,
187
+ size=hf_processor.image_processor.size,
188
+ **kwargs,
189
)
190
return hf_processor
191