Quantization

Advanced quantization technique that applies per-vector normalization and scalar quantization, adapting the quantization bounds individually for each vector. Achieves four-fold reduction in vector size while maintaining search accuracy with 26-37% overall memory footprint reduction.

Extreme vector compression technique converting each dimension to a single bit (0 or 1), achieving 32x memory reduction and enabling ultra-fast Hamming distance calculations with acceptable accuracy trade-offs.

Activation-aware Weight Quantization method that preserves model accuracy at 4-bit quantization by identifying and skipping important weights. Maintains 99%+ of original performance with moderate inference speed improvements.

Post-training quantization method for 4-bit weight compression that focuses on GPU inference performance. First quantization method to compress LLMs to 4-bit range while maintaining accuracy, minimizing mean squared error to weights.

Foundational IR textbook that includes content on vector‑space models and retrieval, providing essential background for understanding vector search and hybrid retrieval in modern vector databases.

A curated list of vector database solutions, libraries, and resources tailored for AI applications. Categorizes items by license and type, providing a valuable directory for those seeking vector database technologies.