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 12, 16:00 UTC
[BugFix] Fix R-VL model loading error (#29299)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
Fanli Lin committed
Nov 24, 2025 at 14:48 UTC
ed40d85929f25a939b8d79ef3f2fb923f5a7bb54
1 file changed
+1
examples/offline_inference/vision_language_multi_image.py
+1
@@ -1110,6 +1110,7 @@ def load_r_vl(question: str, image_urls: list[str]) -> ModelRequestData:
1110
model=model_name,
1111
max_model_len=16384,
1112
max_num_seqs=16,
1113
+ trust_remote_code=True,
1114
limit_mm_per_prompt={"image": len(image_urls)},
1115
)
1116