News for hackers. Stuff that matters.

A comment on Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference. Parent comment

Re:Llama 3.1 405B now runs at 969 tokens/s on Cerebras Infer... by colordrops on Monday November 18, 2024 @10:39PM (#42179907)
Right, I'd assume most LLM benchmarks are run on dedicated hardware.
[ Parent | on HN ]

There are no comments on this comment yet.