AI Dynamics

Global AI News Aggregator

About

Groq Demonstrates Llama-2 70B Inference at 100+ Tokens Per Second

Join today's GroqSpotlight in just 15 minutes and see Groq running the #LLM, Llama-2 70B, at the inference performance of more than 100 tokens per second per user. Watch on LinkedIn or YouTube at https://
youtube.com/watch?v=manwFu
-oC_c
….

→ View original post on X — @groqinc