framework-internalsdevelopment
turboquant-pytorch
PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).
maintainer
Aradotso
更新於 3/28/2026
星標
26
分支
6
quick start
Installation and usage
PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).
安裝
$ install --globalskills.sh
使用
安裝後，您可以通過在終端運行以下命令來使用此技能：
skills use turboquant-pytorch