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 15, 22:15 UTC
[Misc] fixed qwen_vl_utils parameter error (#13906)
Chauncey committed
Feb 27, 2025 at 00:31 UTC
d08b285adfb03f0b7952c8af4c2c83bb2dafcc2d
1 file changed
+1
-1
examples/offline_inference/vision_language_multi_image.py
+1
-1
@@ -439,7 +439,7 @@ def load_qwen2_5_vl(question, image_urls: List[str]) -> ModelRequestData:
439
image_data = [fetch_image(url) for url in image_urls]
440
else:
441
image_data, _ = process_vision_info(messages,
442
- return_video_sample_fps=False)
442
+ return_video_kwargs=False)
443
444
return ModelRequestData(
445
llm=llm,