login sign up

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

cerebras.ai · first added by @hn_wayback
saved by
1 person
discussions · 1
Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference 427 pts · 156 comments · Nov 2024 427 pts · 156 comments · Nov 2024
0 people saved or upvoted this