SSealbook

scrya-com/rotorquant

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

License & maintenance

No license stated: by default nobody may reuse the code. Ask the authors before using it in a product.

Last code push 5 months ago.