Hacker News Reader

I was so excited until I saw that it's CPU based only. Would you happen to know of any alternative for GPU support, particularly GPTQ models?

Edit: I think textgen itself can support this nowadays

View on HN

For now it is CPU only yes, uses AVX instructions. But it's pretty fast anyway, try it out. I have it running on my mbp M1 and it's pretty decent. I think GPU support will come eventually. I wrote an app that uses the openai API and it was nice and simple to just point it at my own local service instead.

Reply on news.ycombinator.com