vllm.transformers_utils.processors ¶
Multi-modal processors may be defined in this directory for the following reasons:
- There is no processing file defined by HF Hub or Transformers library.
- There is a need to override the existing processor to support vLLM.
Modules:
| Name | Description |
|---|---|
bagel | BAGEL processor for image and text inputs. |
deepseek_ocr | |
deepseek_vl2 | |
fireredasr2 | |
funasr | |
glm4v | |
hunyuan_vl | |
hunyuan_vl_image | Image processor class for HunYuanVL. |
ovis | |
ovis2_5 | |
pixtral | |
qwen3_asr | |
qwen_vl | |
voxtral | |