Engram extends standard token embeddings with learned multi-token lookups. Recurring local patterns retrieve vectors directly, reducing the need to reconstruct them through attention and feed-forward ...

Elon Musk shocked the world, once again, when he announced on SpaceX’s first earnings his Gigawatt ambitions for next year. He “conservatively” aims to build & deliver an incremental 6-8GW in 2027 ...

Nvidia’s GB200 brings significant advances in performance via superior hardware architecture, but the deployment complexities rise dramatically. While on the face of it, Nvidia has released a standard ...

We have been spending a lot of time in our private consulting business trying to build out a model of semiconductor fab capital expenditures by tool type for various logic and memory process nodes.

This week we were fortunate enough to attend AMD’s 4th generation Genoa server launch event. For those more concerned about volumes, ASPs, and revenue, check out our deep dive report here.

When we published our first AMD software article, we gave AMD a 0% chance of closing the gap with Nvidia in AI accelerators. Software was broken, progress was unexciting, and we were the top bug ...

The past two months have been a breakout period for open source AI. Yes, there was the “DeepSeek moment” back in January 2025, but no one actually used R1 to do any economically valuable work. In ...

The gold rush for AI infrastructure is creating huge opportunities for the companies supplying enabling technologies. Not everyone is an Nvidia in this infrastructure build out bonanza, there are many ...

ACM Research was founded in 1998 by Dr. David Wang focused on developing and selling stress-free copper polishing tools which were positioned as a competitor to chemical metal planarization (CMP). ACM ...

Tokens and burgers are not two ideas you often see paired in the same title. If you’re wondering what they could possibly have in common, stick with us for this short piece, because today we’re ...

At GTC, Nvidia announced 8+ different SKUs and configurations of the Blackwell architecture. While there are some chip level differences such as memory and CUDA core counts, most of the configurations ...

Graphcore is announcing their newest AI accelerator, Bow. For the most part, the architecture is completely identical, except one massive change to system design. The introduction of 3D wafer-on-wafer ...