vector-quantization

Vector (and Scalar) Quantization, in Pytorch

[EMNLP 2024] ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement

PostgreSQL TurboQuant Index for PGVector

The data layer for AI with Vector, Graph and Vector-Math built into one single rust engine

Out-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.