56,000+ tokens/sec at just 80 MHz. 🤯 I burned a full Transformer with KV cache into a custom chip. Designed gate by gate as a 100% digital integrated circuit. Prototyped on a FPGA. (No GPU. No CPU) Just pure digital silicon running @karpathy microGPT,

We Hit 120 Tokens Per Second With 1 Million Token Context on a Single Desktop AI Computer

How We Optimised a 229 Billion Parameter AI Model on a Desktop Computer: A 12-Phase Journey

New device promises 1,000x faster processors without extra waste heat, but details are scarce

This article briefly describes a new device that could enable computer processors to run up to 1,000 times faster without generating additio

Researchers Serve 229B-Parameter MoE Model Across Five Consumer GPUs Over Public Internet

This article describes a technical demonstration where a 229-billion parameter Mixture-of-Experts AI model (MiniMax-M2.5) is served across f

Study claims Pearl blockchain's 320,000 GPUs consume 112 megawatts with zero useful AI computation

A new research preprint claims that Pearl, a Layer-1 blockchain marketed as turning cryptocurrency mining into useful AI computation, is act

Are plug-in DERs going to spark a grid revolution?