News for hackers. Stuff that matters.

A comment on Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs. Parent comment

Re:Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs by pama on Thursday August 07, 2025 @07:17AM (#44823063)
If you want to go down the rabbit hole of the state of the art, I recommend the EAGLE3 paper: https://arxiv.org/abs/2503.01840
[ Parent | on HN ]

There are no comments on this comment yet.