$NVDA's Groq 3 LPX Enters Full Production, $NBIS First to Deploy

Nvidia's Groq 3 LPX inference accelerator is now in full production, with Nebius ($NBIS) set to become the first AI cloud to deploy it.
The new inference stack pairs Rubin GPUs for heavy context processing with Groq 3 LPX for ultra-fast token generation, giving Nebius a purpose-built architecture for faster agentic AI.