Quantization - Simulations

Project information

Following Google's TurboQuant release (https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/), this repository contains two KV cache quantization simulations (KMeans codebook and TurboQuant-style rotation) to explore core quantization principles.

Inspired by: https://medium.com/@gautsoni/llm-quantization-the-practical-guide-and-why-it-matters-for-inference-and-training-8668f4b91dcc

1 Commit
1 Branch
0 Tags

README

Created on

July 18, 2026

Loading