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, 13:30 UTC
[Docs] Fix True->true in supported_models.md (#17141)
Michael Goin committed
Apr 24, 2025 at 22:20 UTC
649818995f60b410a57059445ec1d66f8db347b5
1 file changed
+3
-3
docs/source/models/supported_models.md
+3
-3
@@ -1082,7 +1082,7 @@ See [this page](#generative-models) for more information on how to use generativ
1082
1083
:::{important}
1084
Pan-and-scan image pre-processing is currently supported on V0 (but not V1).
1085
-You can enable it by passing `--mm-processor-kwargs '{"do_pan_and_scan": True}'`.
1085
+You can enable it by passing `--mm-processor-kwargs '{"do_pan_and_scan": true}'`.
1086
:::
1087
1088
:::{warning}
@@ -1097,7 +1097,7 @@ V0 correctly implements the model's attention pattern:
1097
1098
V1 currently uses a simplified attention pattern:
1099
- Uses causal attention for all tokens, including image tokens
1100
-- Generates reasonable outputs but does not match the original model's attention for text + image inputs, especially when `{"do_pan_and_scan": True}`
1100
+- Generates reasonable outputs but does not match the original model's attention for text + image inputs, especially when `{"do_pan_and_scan": true}`
1101
- Will be updated in the future to support the correct behavior
1102
1103
This limitation exists because the model's mixed attention pattern (bidirectional for images, causal otherwise) is not yet supported by vLLM's attention backends.
@@ -1129,7 +1129,7 @@ To use Qwen2.5-Omni, you have to install Hugging Face Transformers library from
1129
`pip install git+https://github.com/huggingface/transformers.git`.
1130
1131
Read audio from video pre-processing is currently supported on V0 (but not V1), because overlapping modalities is not yet supported in V1.
1132
-`--mm-processor-kwargs '{"use_audio_in_video": True}'`.
1132
+`--mm-processor-kwargs '{"use_audio_in_video": true}'`.
1133
:::
1134
1135
### Pooling Models