tonbistudio/turboquant-pytorch

From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.

2 best points · 0 comments · 1 Hacker News post · 1,047 GitHub stars · View on GitHub

Hacker News discussions

• 10-19x faster alternative to TurboQuant via Clifford rotors (44x fewer params) (2 points, 0 comments, by hochmartinez, 2026-04-03)