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
[Misc] fix typo in the multimodal doc (#23051)
Kevinzz committed
Aug 17, 2025 at 16:56 UTC
16bff144be6739c9f773968ace0b9cd239f67f19
1 file changed
+1
-1
docs/features/multimodal_inputs.md
+1
-1
@@ -216,7 +216,7 @@ Instead of NumPy arrays, you can also pass `'torch.Tensor'` instances, as shown
216
from vllm import LLM, SamplingParams
217
from qwen_vl_utils import process_vision_info
218
219
- model_path = "Qwen/Qwen2.5-VL-3B-Instruct/"
219
+ model_path = "Qwen/Qwen2.5-VL-3B-Instruct"
220
video_path = "https://content.pexels.com/videos/free-videos.mp4"
221
222
llm = LLM(