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, 23:45 UTC
Fix typo for limit-mm-per-prompt in docs (#21697)
Signed-off-by: Joachim Studnia <joachim@mistral.ai>
Joachim Studnia committed
Jul 27, 2025 at 19:45 UTC
82acf2184d042135b5bc7584f68535ff67819343
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -3258,7 +3258,7 @@ class MultiModalConfig:
3258
Defaults to 1 (V0) or 999 (V1) for each modality.
3259
3260
For example, to allow up to 16 images and 2 videos per prompt:
3261
- `{"images": 16, "videos": 2}`
3261
+ `{"image": 16, "video": 2}`
3262
"""
3263
3264
media_io_kwargs: dict[str, dict[str, Any]] = field(default_factory=dict)