Yeah they are. llama.cpp has had good performance on cpu, amd, and apple metal f... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		fzzzy 5 days ago \| parent \| context \| favorite \| on: OpenAI declares 'code red' as Google catches up in... Yeah they are. llama.cpp has had good performance on cpu, amd, and apple metal for at least a year now.

tomrod 5 days ago [–]

Thw hardware is not the issue. It's the model architectures leading to cascading errors

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact