CoruNethron

@WojtekKowaluk , thank you for this fix @clarklight , I've tested on M1 SoC 16GB as well and it achieves 8-10 seconds per iteration in my case, but you can...

@clarklight there is no CUDA support in GPU, that's correct. But there is support for another acceleration on the GPU, that's `mps`, and it can utilize Mac silicon GPU with...

@clarklight I took some ideas about image export with unique file name here: https://gist.github.com/FurkanGozukara/10bdc0435b708b26bd87a59b6c3d1bc7

Closing this, as Qwen inference has being added few days ago: https://github.com/QwenLM/qwen.cpp

Sorry for increasing entropy here, just realized, that recently implemented inference is for another model: https://github.com/QwenLM/Qwen vs https://github.com/QwenLM/Qwen-VL So, I reopen this feature request.