skills.homes logoskills.homescapability registry
home/categories/framework-internals/aradotso-trending-skills-skills-turboquant-pytorch-skill-md
cd ..
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).

View Sourceframework-internals
Aradotso
maintainer
Aradotso
Updated 3/28/2026
Stars
26
Forks
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).

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use turboquant-pytorch