Vector Quantization Python Packages

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

minisom

:red_circle: MiniSom is a minimalistic implementation of the Self Organizing Maps

annlite

Fast and Light Approximate Nearest Neighbor Search Library integrated with the Jina Ecosystem

nexusquant-kv

Training-free KV cache compression via E8 lattice quantization; fits longer context in the same VRAM

dbgsom

A scikit-learn compatible Python implementation of the Directed Batch Growing Self-Organizing Map

time-causal-vae

Time-causal financial generative models: refactored TC-VAE baselines with causal VQ/RVQ tokenizers, token priors, S&P500/VIX, Hawkes/SVMHJD, multi-dimensional benchmarks, and path-risk diagnostics.

swarndb

Official Python SDK for SwarnDB, the vector database that thinks in graphs. Combines HNSW + IVF-PQ indexing with virtual graph traversal and 15+ vector math operations.

helix-substrate

Model weight compression and streaming decode library

titok-pytorch

Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"

turboquant-space

TurboQuant (ICLR 2026) — SIMD-accelerated 4/8-bit quantization Space for ANN

pyvq

Python bindings for the Vq library

timevqvae

Vector-quantized time-series generation with a bidirectional prior model.