Turboquant Pytorch

by reason-machines2384a003145aNo license83 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 months ago

PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).

Only the file list is public. File contents are available once the skill is installed in a workspace.

PathSizeType
SKILL.md13.5 KBtext/markdown

Source and attribution

Source:reason-machines/trending-skillsinskills/turboquant-pytorchat commit2384a00

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal