New architecture proposes shifting static pattern storage to cheaper memory types In sum – what we know: Billions have flowed into GPU infrastructure over the past few years, and high-bandwidth memory has …

The chip’s huge memory could offer a unique niche for AI inference workloads In sum – what we know: Nvidia’s leadership on AI silicon has looked pretty much unshakeable for …

Nvidia Vera Rubin is technically a big improvement — but potential customers are still working on their own hardware In sum – what we know: Nvidia CEO Jensen Huang took …

One stop at a time Author’s note: I’m one of those AuDHD people you encounter in tech, media and tech media. CES and Las Vegas are exhausting, but I wanted …

You don’t have to own the hardware for AI. But should you? Every organization building with AI eventually has to decide whether to own the hardware or rent it. This …

Will open-source chips democratize the industry? In the early 1990s, a Finnish student named Linus Torvalds released a free operating system kernel called Linux. This new operating system, together with …

Non-exclusive agreement transfers key talent and technology while Groq remains independent In sum – what we know: Nvidia and chip startup Groq have announced a non-exclusive licensing agreement reportedly worth around $20 …

The deal could see OpenAI train its new models on Amazon silicon In sum – what we know: Amazon is reportedly in early discussions to invest as much as $10 …

The prototype shows how vertically stacked logic and memory could unlock major AI performance gains In sum – what we know: A collaboration between Stanford, Carnegie Mellon, University of Pennsylvania, and …

Chipmaker outlines strategy for electrical and optical AI infrastructure to capture growing market share In sum – what we know: Marvell Technology is going through some changes. Shifting focus from …