AmazDeng

The OneVision-7B Demo is unable to return a result.[bug]

1

There are some issues with the online OneVision-7B Demo. When two images are input for inference, it fails to return a result. @Luodian @ZhangYuanhan-AI @Luodian 

InternVL2-40B-AWQ+lmdeploy video infer speed is very slow

16

I am using the InternVL2-40B-AWQ model and performing video inference according to the multi-images inference paradigm. Each video is sampled into 24 frames, and the prompt is as follows. My...

[Bug] InternVL2-Llama3-76B-AWQ infer result is wrong

9

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...

the output of onnx model is different from model inferenced by TensorRT

7

## Description I attempted to compile a Hugging Face model (the Hugging Face model link is: https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5, which includes both the model architecture code and model files) using TensorRT (TRT)...

I've noticed that the latest version of ColossalAI does not support 2D, 2.5D, and 3D tensor parallelism. I would like to know, according to ColossalAI's roadmap, when Shardformer will support...

flux lora train support

4

@FrankLeeeee @gothicx @tiansiyuan @jeffra Does ColossalAI support training Flux model? For example, if I'm using a LoRA paradigm and need to redefine the processor within Flux, is this training method...