shuhanyao

> What error are you getting and how are you loading the model? > > [Documentation](https://huggingface.co/OpenGVLab/InternVL3-78B) on hugging face may provide more clarity on batch inference when using Transformers batch_chat中的image_token的替换逻辑，如果有多个占位符其实不会都被替换为image_tokens的？chat()中是遍历num_patches进行替换...

> We suggest you to use LMDeploy for multi-image batch inference. You can refer to their [document](https://lmdeploy.readthedocs.io/en/latest/multi_modal/vl_pipeline.html#multi-images-inference). > > If you want to infer with transformers backend, you can refer...