I run models using HF just fine. I mean I’m using HF transformers repo, which gets models from HF hub.
Or do you mean commercial deployment of models for inference?
Or do you mean commercial deployment of models for inference?
My understanding is the modern quantization algorithms are typically implemented in Pytorch.
The only thing I know (from using it) that with quantization I can fit models like llama2 13b, in my 24GB of VRAM when I use q8 (16GB) instead of fp16 (26GB). This means I can get nearly the full quality of llama2 13b's output while still being able to use only my GPU, without the need to do very slow inference on only CPU+RAM.
And the models are quantized before inference, so I'd only download 16GB for the llama2 13b q8 instead of the full 26GB, which means it's not done on the fly.
I don't know why I still do it, but everytime I read so many comments how good model X is, and how it outperforms anything else, and then I want to see it for myself.