d-Matrix signs up Nvidia’s NVLink Fusion
AI inference chipmaker d-Matrix is plugging its forthcoming Raptor accelerators into Nvidia’s NVLink Fusion ecosystem,…
AI inference
Qualcomm lands $60 billion Amazon AI chip deal
Qualcomm has struck a long-term deal with Amazon covering up to $60 billion in AI…
OpenAI’s Jalapeño benchmarks beat Nvidia GB300
OpenAI has published its own Jalapeño benchmark numbers, claiming its 700W inference ASIC can outpace…
Vera Rubin makes Blackwell look pricey
Nvidia claims Vera Rubin can churn agentic AI tokens far more cheaply than Blackwell. Writing…
IBM stuffs Arm into Z core
Biggish Blue has bolted Arm into its big iron without turning its mainframe into a…
AMD buys inference silicon outfit Taalas
AMD has snapped up Taalas to give its AI inference plans another shove beyond its…
Cerebras gives AMD a smug moment
AMD’s Cerebras has picked up an OpenAI compliment, giving Helios a shine no amount of…
Unconventional AI wants to rebuild computing
Unconventional AI reckons ordinary chips are too thirsty, so it wants to rebuild AI computing…
AMD and Intel smoke peace pipe to fix x86 AI
AMD and Intel have published the full specification for AI Compute Extensions, better known as…
AWS cranks out Graviton5
Amazon Web Services has made its Graviton5 CPU generally available, giving cloud customers another Arm-based…