It's mechanically capable of per-token routing, but the routing tends to be stab... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

regularfry 59 days ago | parent | context | favorite | on: What happens if we remove 50 percent of Llama?

It's mechanically capable of per-token routing, but the routing tends to be stable across more than one token. It's weird.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact