Sparse Embedding Compression for Scalable Retrieval in Recommender Systems

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

Vector compression with TurboQuant codecs for embeddings, retrieval, and KV-cache. 10x compression, pure NumPy core — optional GPU acceleration via PyTorch (CUDA/MPS) or MLX (Metal).

Compress embeddings, retrieval vectors, and KV-cache with TurboQuant codecs for 10x smaller storage and NumPy-first AI workloads

A PyTorch Framework for Sparse Representation Learning

TurboQuant (ICLR 2026) vector quantization for memory/RAG embedding compression | 5-8x压缩 98%+召回率 | numpy only, no GPU