Labs' open kernels are clearly written for Blackwell, bolstering GPU fingerprinting claims
a1zhang · x · 2026-11-13
Responding to GPU-fingerprinting analysis of which chips trained frontier models, a1zhang notes it's less that Blackwell is a strict requirement and more that recently released open infra and kernels from these labs are clearly written for Blackwell, especially lower-precision code.
- He expresses no view on the blog's estimate figures
- Declines to weigh in on export-control implications as purely speculative
- But agrees with the plain conclusion: the fingerprinted GPUs were likely the ones used for training
More from Infra
- 'Maybe the Great Filter Is Permitting a 10GW Data Center' Quip Resonates — Dr_Singularity · 2026-11-13
- Fab capacity jumps to 1.117M 8-inch-equivalent wafers/month, 78.9% on 12-inch — teortaxesTex · 2026-11-13
- Microsoft and Claude go down simultaneously, taking apps offline with them — ThePeterMick · 2026-11-13
- llama.cpp ships v1.0.0, the landmark first stable release for local LLM inference — TheApadayo · 2026-11-13
- Singapore files 41 charges against man in alleged Nvidia AI chip smuggling scheme to Malaysia — Polymarket · 2026-11-13
- Meme: All modern digital infrastructure rests on one tiny Model Hub pillar — pcuenq · 2026-11-13