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

Not even single batch. If you want reasonable latency per token (TPOT) even larger batches do not give you high compute utilization during extend. It’s only when you don’t care about TPOT at all, and your model is small enough to leave space for a large batch on an 8 GPU host, that’s when you could get decent utilization. That’s extend only - it’s easy to get high utilization in prefill.


Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: