My daily struggle is trying to make a 7B model respond in under 500ms without br... | Hacker News

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

clem_rw 20 days ago | parent | context | favorite | on: The efficient frontier of LLM inference

My daily struggle is trying to make a 7B model respond in under 500ms without breaking the bank. This hits home.

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