KerwinKai

I'm currently doing the prep work on this and would like to ask if the conversion is technically possible

[CodeCamp2023-305] Improve Visualizer Rendering Speed with OpenCV Backend

20

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

您好，我使用mobilenetv1时会产生relu6层，但是该工具还不支持这一层的转换，想咨询下如何添加代码来支持这一层的转换。

Add Eagle3 training for more MLLM model

9

## Motivation In addition to the previously supported qwen2.5 vl, more multimodal language models have emerged, such as omni, dsvl, internvl, qwen3vl, etc. An abstract solution needs to be designed...

[Feature] VLM model support tp

3

## Motivation support tp for qwen2.5 vl, the gpu memory is 78.62GB in tp1, 43.56GB in tp4. ## Modifications - add qwen2_5_vl.py for target model - add `QKVParallelLinear` for linear.py,...