GitHub

Vector Search using Embeddings, FAISS and Product Quantization

This project implements an efficient similarity search system for lecture content using embeddings, FAISS and Product Quantization with custom index & KMeans implementations. It allows you to find ...
GitHub

3D_VQ-VAE_pytorch

An example implementation of a three-dimensional (3D) Vector-Quantized Variational Autoencoder (VQ-VAE) prototype, here used for the compression task of 3D data cubes. This 3D VQ-VAE is an extension ...
IEEE

Generalized Residual Vector Quantization and Aggregating Tree for Large Scale Search

Abstract: Vector quantization is an essential tool for tasks involving large scale data, for example, large scale similarity search, which is crucial for content-based information retrieval and ...
Microsoft

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models

Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only ...