Search

spectrum.ieee.org › tensordyne-inference-claim

Tensordyne's Wild Log Math Aims to Leave Nvidia’s AI Chips In the Dust

… Tensordyne executives say they saw this coming and engineered their computers to meet it. Tensordyne’s Napier AI chip includes 144 gigabytes of HBM, but the real power comes from its unusual math. Tensordyne There are two main parts to executing an LLM: prefill and decode. …

Jun 15, 2026 · Samuel K. Moore

spectrum.ieee.org › nvidia-groq-3

Nvidia’s Groq 3 LPU Signals AI's Inferencing Era

… The startups include D-matrix , with digital in-memory compute; Etched , with an ASIC for transformer inference; RainAI , with neuromorphic chips ; EnCharge , with analog in-memory compute; Tensordyne , with logarithmic math to make AI computations more efficient; FuriosaAI , with hardware optimize… …

Mar 16, 2026 · Dina Genkina