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

cformers already has ggml support because it's the same architecture as GPT-NeoX.

llama.cpp just added preliminary support three hours ago. https://github.com/ggerganov/llama.cpp/issues/1063#issuecomm...



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

Search: