Re:Real-time LLM Inference on Standard GPUs: 3k tokens/s per...
by dchftcs on Friday May 29, 2026 @12:00PM
(#48324956)
An article with a title saying tokens per second throughput without any qualifier e.g. what size the model is should immediately be classified as spam.
[ Parent
| on HN ]
There are no comments on this comment yet.