Verified record · from the answer index
turboquant-pytorch
skilltested · static-verifiedscore 49/100signed passport ✓815 uses
PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).
Declared tools (1)
turboquant-pytorch
skill:reason-machines/trending-skills/turboquant-pytorch · published by reason-machines · source repository