AMD Instinct 455X targets Nvidia’s Rubin directly
320 billion transistors, 72-GPU rack scale—Scale up, scale out.
Rubin makes inference a rack problem
The emphasis turns to memory, power, and racks as interconnected parts of the puzzle
AI processor architectures are evolving almost as fast as LLMs are
AGI will not be realized with just more clever software.
Nvidia’s Groq tie-in
Why Nvidia keeps making smart decisions.
Nvidia GTC 2026 keynote
The AI leader shows how it will continue to lead.
AI: Everything everywhere all at once
Even at CES, AI really isn’t the answer to everything.
Nvidia, the everything company
GPUs, cars, networking processors, robots, supercomputers, gaming chips, rice cookers.
AI training vs. inferencing vs. memory bandwidth
Getting closer to very fast memory is the key.
Nvidia prepares Vera Rubin for next AI wave
Powerful CPU+GPU chip expected by 2027.