Groq

Groq is an AI infrastructure company that provides ultra-fast inference for large language models through its custom-designed Language Processing Unit (LPU) hardware and cloud API. Founded in 2016 by Jonathan Ross, who previously led the development of Google's Tensor Processing Unit (TPU), Groq has built purpose-designed semiconductor chips optimized specifically for the sequential nature of language model inference, achieving dramatically lower latency and higher throughput compared to trad...

Threads