Microsoft builds Maia 300 to trim Nvidia bills
Software King of the World, Microsoft has unveiled its Maia 300 AI accelerator and plans…
hbm4
Micron ramps HBM4 as AI memory race tightens
Micron is pushing harder into HBM as AI demand turns high-bandwidth memory into one of…
OpenAI’s Jalapeño benchmarks beat Nvidia GB300
OpenAI has published its own Jalapeño benchmark numbers, claiming its 700W inference ASIC can outpace…
SK Hynix tries to stop HBM cooking itself
SK Hynix is trying to keep HBM from cooking itself as demand for AI chips…
Samsung HBM4 yield gives AI rivals something to chew on
Samsung’s HBM4 yields are reportedly closing in on 80 per cent, giving it a better…
AMD shows off Helios AI rack monster
AMD has rolled out its Helios AI rack, a liquid-cooled monster designed to pick a…
Zen 6 push nears AMD to trillion-dollar mark
AMD’s 2nm server silicon and AI rack plan have pushed its valuation close to a…
Nvidia plants flag in Europe’s science clouds
Nvidia used ISC 2026 to flog Vera Rubin as Europe’s new science engine, which sounds…
Nvidia’s memory bill goes daft
Nvidia’s Vera Rubin rack bill shows memory prices going bananas as AI hardware turns into…