Groq

Groq is a chip startup that has developed the Language Processing Unit (LPU), custom silicon designed specifically for LLM inference. Their hardware delivers inference speeds 10-25x faster than GPU-based alternatives, making real-time AI applications practical.

Founded in 2016 by Jonathan Ross, a former Google TPU architect. Spent years in stealth building the LPU. Burst into public awareness in early 2024 when their publicly accessible API demonstrated inference speeds of 500+ tokens/second for Llama and Mixtral.