A curated list of 120+ LLM libraries category wise.

AIOS: AI Agent Operating System

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

GeminiFS: A Companion File System for GPUs

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Magnum IO community repo

A Survey on Multimodal Retrieval-Augmented Generation

Build userspace NVMe drivers and storage applications with CUDA support

XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

NVIDIA GPUDirect Storage Driver

cuVS - a library for vector search and clustering on the GPU

Retrieval and Retrieval-augmented LLMs

ESPN: Embedding from Storage Pipelined Network. GDS implementation for multi-vector embedding retrieval and bindings.

Web-scale retrieval for knowledge-intensive NLP

Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest neighbor search methods, or vector indexes, using modern embedding datasets.

A library for efficient similarity search and clustering of dense vectors.

Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

Benchmark baseline for retrieval qa applications

Official repository of the MIRAGE benchmark

Comprehensive benchmark for RAG

Text describing xv6 on RISC-V

Commentary for xv6-public

A high-throughput and memory-efficient inference and serving engine for LLMs

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.