Gentlemen (and women), start your inference engines. One of the world’s largest buyers of systems is entering evaluation mode for deep learning accelerators to speed services based on trained models.

1. Flex Logix’s nnMAX 1K inference tile delivers INT8 Winograd acceleration that improves accuracy while reducing the necessary computations. The InferX X1 chip includes multiple nnMax clusters. It ...

FriendliAI — founded by the researcher behind continuous batching, the technique at the core of vLLM — is launching InferenceSense, a platform that fills idle neocloud GPU capacity with paid AI ...

SANTA CLARA – Today, d-Matrix, a AI-compute and inference company, announced a collaboration with Microsoft using its low-code reinforcement learning (RL) platform, Project Bonsai, to enable an ...

A Korean research team has unveiled a core technology which reduces the time and cost invested in developing artificial intelligence (AI) chips in small and medium-sized enterprises and startups.