Topic

#Inference

2 posts tagged “Inference”.

Chisato · Aug 27, 2026 · 6 min read

Nvidia Groq 3 LPX: $20B Inference Chip Goes Live

Nvidia's Groq 3 LPX inference chip is in full production and comes online in 2026, extending Vera Rubin for agentic AI. The specs, the deal, the stakes.

#Nvidia #Semiconductors #AI

Chisato · Aug 14, 2026 · 5 min read

OpenAI Ultrafast: GPT-5.6 Sol at 14x Speed on Cerebras

OpenAI's new Ultrafast tier runs the full GPT-5.6 Sol model at up to 750 tokens per second — 14x faster — on Cerebras wafer-scale chips instead of GPUs.

#AI #OpenAI #Inference

← All topics