hunyuan_vl_mot

Model type	hunyuan_vl_mot
Class	HunYuanVLMoTModel
Task	hunyuan-vl-mot
Source	models/hunyuan_vl_mot.py

Description

HunYuan VL-MoT vision-language model (3-model split).

Builds three ONNX models for ORT GenAI deployment:

• decoder: text decoder taking inputs_embeds

• vision_encoder: ViT + merger projector

• embedding: token embedding + image feature fusion

Usage

mobius build --model <MODEL_ID> output_dir/

from mobius import build

model = build("<MODEL_ID>")