turboquant

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss. Maintained by OnlyTerp on GitHub, where it has earned 76 stars from the community.

It's actively developed around attention, compression, deep-learning, and is a solid reference for anyone building with these tools.