Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference

(cerebras.ai)

426 points benchmarkist | 1 comments | 19 Nov 24 00:15 UTC | HN request time: 0.199s | source

1. xwww ◴[19 Nov 24 06:51 UTC] No.42180666[source]▶

Transistor（GPU）-> Integrated Circuit (WSE-3)