A library of GPU kernels for sparse matrix operations.

Self-hosted file/code/media sharing website. ~~~~~~~~~~~~~~~~~~~ Powers https://put.icu

Helpful tools and examples for working with flex-attention

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Distributed Training Over-The-Internet

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A lightweight library for portable low-level GPU computation using WebGPU.

Python package for reading and writing uncompressed yuv image and video data.

#1 Locally hosted web application that allows you to perform various operations on PDF files

A C++ implementation of a LRU cache

DataComp for Language Models

Evaluating LLMs with Dynamic Data

A new bootable USB solution.

Tile primitives for speedy kernels

A CPU tool for benchmarking the peak of floating points

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

🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers

A C++20 header-only library that supports powerful reflection for C++

MSCCL++: A GPU-driven communication stack for scalable AI applications

A validation and profiling tool for AI infrastructure

TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches

🌱Light and powerful C++ web framework for highly scalable and resource-efficient web application. It's zero-dependency and easy-portable.

Universal cross-platform tokenizers binding to HF and sentencepiece

CUDA Templates for Linear Algebra Subroutines

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

UTF-8 with C++ in a Portable Way

The home of the ICU project source code.

A lightweight JIT compiler based on MIR (Medium Internal Representation) and C11 JIT compiler and interpreter based on MIR