Vector Quantization

Vector quantization replaces continuous vectors with indices into a set of representative codewords, reducing storage and creating discrete tokens for models. Common approaches learn codebooks with autoencoders, use residual or product quantization, or impose geometric structure such as lattices and spheres; they are evaluated on image and audio reconstruction, vector retrieval, language-model quality, and inference speed. Applications range from visual and speech tokenizers to compressed LLM weights and attention caches, where specialized kernels can determine whether smaller representations also run faster. A central tension is preserving task-relevant information at very low bit rates while avoiding codebook collapse, calibration costs, and hardware overhead; utilization alone does not guarantee low distortion or strong downstream results.