This project aims at building a scalable transactional stream processing engine on modern hardware. It allows ACID transactions to be run directly on streaming data. It shares similar project visio…

lzbench is an in-memory benchmark of open-source compressors

Zstandard - Fast real-time compression algorithm

New generation entropy codecs : Finite State Entropy and Huff0

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

LongBench v2 and LongBench (ACL 25'&24')

A large collection of system log datasets for AI-driven log analytics [ISSRE'23]

Some quick and dirty Postgres benchmarks

Silesia compression corpus

Awesome LLM compression research papers and tools.

Perf monitoring CLI tool for Apple Silicon

Examples in the MLX framework

MLX: An array framework for Apple silicon

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

The official GitHub page for the survey paper "A Survey of Large Language Models".

The definitive Web UI for local AI, with powerful features and easy setup.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

FlashInfer: Kernel Library for LLM Serving

A time-series database for high-performance real-time analytics packaged as a Postgres extension

SpotServe: Serving Generative Large Language Models on Preemptible Instances

Hackable and optimized Transformers building blocks, supporting a composable construction.

An easy to use PyTorch to TensorRT converter

A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.

Apache HBase

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support