vllm.models.step5.nvidia.vl

Inference-only Step5 vision-language model.

Classes:

• Step5ForConditionalGeneration –

  Step5 VLM using the Step3p7 multimodal frontend and Step5 text model.

Step5ForConditionalGeneration

Bases: Step3p7ForConditionalGeneration

Step5 VLM using the Step3p7 multimodal frontend and Step5 text model.

Source code in vllm/models/step5/nvidia/vl.py

class Step5ForConditionalGeneration(Step3p7ForConditionalGeneration):
    """Step5 VLM using the Step3p7 multimodal frontend and Step5 text model."""