#GPU
4 articles tagged GPU. At twelve articles this topic starts lifting the whole site in search.
Timeline
-
What Grace Blackwell NVL72 is — a rack that behaves like one GPU
-
Nvidia pauses its revenue-sharing program — a July launch stopped in under two months
-
What an AI inference chip is — why companies build separate silicon from training GPUs
-
What GPU depreciation is — change one number and an AI company's profit changes
All articles
-
Tech · 2 min readWhat Grace Blackwell NVL72 is — a rack that behaves like one GPU
Definition — a rack, not a chip: 36 Grace CPUs and 72 Blackwell GPUs bound by a two-tier NVLink fabric and addressed as one accelerator
-
Tech · 3 min readNvidia pauses its revenue-sharing program — a July launch stopped in under two months
What — Parts of the AI Compute Partnership, launched July 2026, paused. Under two months in
-
Tech · 4 min readWhat an AI inference chip is — why companies build separate silicon from training GPUs
Split — Training builds a model, inference runs it. The frequency and the requirements are fundamentally different
-
Tech · 4 min readWhat GPU depreciation is — change one number and an AI company's profit changes
Mechanism — a GPU's cost is not expensed in the year of purchase but spread across its assumed useful life