ThunderKittens now runs on NVIDIA Rubin: 22 and 12 PFLOPS on nvfp4/fp8 GEMMs, rivaling cuBLAS
simran_s_arora · x · 2026-09-11
Together AI's kernels team got early access to NVIDIA Vera Rubin NVL72 and ported ThunderKittens to Rubin in days, digging through the new ISA to bring up nvfp4 and fp8 GEMMs—pushing past 22 and 12 PFLOPS respectively, competitive with cuBLAS and the Cute DSL.
Related event: ThunderKittens Lands on Vera Rubin: NVFP4 GEMM Tops 22 PFLOPS(7 posts)→
More from Infra
- Anthropic's $430B compute contracts are noncancelable, topping China's military budget — xiaosun86 · 2026-10-27
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27