papasani\mohan/srinivas

icon indicating a website link https://papasanimohansrinivas.github.io/ icon indicating an email [email protected]

icon location Hyderabad icon location I am working on ML integration and deployment aspects in current organization.

Results 6 comments of papasani\mohan/srinivas

convert pth to onnx

plus+1 i also have requirement to convert the model to onnx to use it on opencv kindly help here @zylo117 it will be a huge help !

[Question] Can LLava inference on CPU?

you need to install torch cpu and set device map to cpu in model loading side @wenli135

C++ Version of Qwen-VL?

please make it the priority @simonJJJ

C++ Version of Qwen-VL?

@simonJJJ can you tell us otherwise how to increase throughput on qwen-vl-chat-int4 any optmization techniques please

Would it be possible to open up the source code of the inference script instead of the gradio script?

same here @code10086web kindly open source the inference code @iFighting @wjf5203

Would it be possible to open up the source code of the inference script instead of the gradio script?

hi @code10086web i have verified your script with my own inputs and against those same inputs with gradio demo , I am finding slightly different results @iFighting @wjf5203