Stéphane ANCELOT
Stéphane ANCELOT
I am using your branch ... this is why I don't really understand ...
OK. I found the pb, it was using a conflicting cgal header installed in the system. Thanks.
I have exactly similar problem. I am trying to run it under MSYS2/Mingw64 because it is a unix like environment, where I could easily package ROS. colcon provides me powershell...
I fully agree with you ..... using docker is a pain. it would have been nice if you had provided how you proceed ^^ # backend cd backend python -m...
You are rights, documentation is not accurate the value is not returned to ouput : the js function takes input,output as parameters so you would need to return outputs for...
On my windows system, altough files have been downloaded, it does not find them, since it does not look in the right folder in face_analysis.py file, replace onnx_files = glob.glob(osp.join(self.model_dir,...
At first I deactivated Intel Video , to keep only Nvidia GPU. => cpu is always used. I setted up : OLLAMA_FLASH_ATTENTION=1 OLLAMA_LLM_LIBRARY="cuda_v11" CUDA_VISIBLE_DEVICES=0 => Now, I can see that...
@manualsh it works using dedicated async python3 syntax. Nothing related to any llm.only a documentation example to correct....
Oh very sorry . This is a gradio bug I filled in the wrong project