xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 11:06:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Docs] Fix True->true in supported_models.md (#17141)

Browse Source
This commit is contained in:
Michael Goin 2025-04-24 22:20:04 -06:00 committed by GitHub
parent 7a0a9da72b
commit 649818995f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/models/supported_models.md
View File

@ -1082,7 +1082,7 @@ See [this page](#generative-models) for more information on how to use generativ
:::{important} :::{important}
Pan-and-scan image pre-processing is currently supported on V0 (but not V1). Pan-and-scan image pre-processing is currently supported on V0 (but not V1).
You can enable it by passing `--mm-processor-kwargs '{"do_pan_and_scan": True}'`. You can enable it by passing `--mm-processor-kwargs '{"do_pan_and_scan": true}'`.
::: :::
:::{warning} :::{warning}
@ -1097,7 +1097,7 @@ V0 correctly implements the model's attention pattern:
V1 currently uses a simplified attention pattern: V1 currently uses a simplified attention pattern:
- Uses causal attention for all tokens, including image tokens - Uses causal attention for all tokens, including image tokens
- Generates reasonable outputs but does not match the original model's attention for text + image inputs, especially when `{"do_pan_and_scan": True}` - Generates reasonable outputs but does not match the original model's attention for text + image inputs, especially when `{"do_pan_and_scan": true}`
- Will be updated in the future to support the correct behavior - Will be updated in the future to support the correct behavior
This limitation exists because the model's mixed attention pattern (bidirectional for images, causal otherwise) is not yet supported by vLLM's attention backends. 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
`pip install git+https://github.com/huggingface/transformers.git`. `pip install git+https://github.com/huggingface/transformers.git`.
Read audio from video pre-processing is currently supported on V0 (but not V1), because overlapping modalities is not yet supported in V1. Read audio from video pre-processing is currently supported on V0 (but not V1), because overlapping modalities is not yet supported in V1.
`--mm-processor-kwargs '{"use_audio_in_video": True}'`. `--mm-processor-kwargs '{"use_audio_in_video": true}'`.
::: :::
### Pooling Models ### Pooling Models