BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

Differentiable signal processing on the sphere for PyTorch

The core of our monitoring platform with a powerful configuration language and REST API.

A Rust-based embedded operating system designed to enable memory safe, memory efficient, reliable, and responsive applications.

Rapid is a scalable distributed membership service

cuGraph - RAPIDS Graph Analytics Library

Optimized primitives for collective multi-GPU communication

NVIDIA device plugin for Kubernetes

A Collection Of The State-of-the-art Metaheuristic Algorithms In Python (Metaheuristic/Optimizer/Nature-inspired/Biology)

Google core libraries for Java

CUDA Core Compute Libraries

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

RLScheduler: An AutomatedHPC Batch Job Scheduler Using Reinforcement Learning [SC'20]

Slurm: A Highly Scalable Workload Manager

Highly Efficient FFT for Exascale

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

📐 Jekyll theme for building a personal site, blog, project documentation, or portfolio.

A beautiful, simple, clean, and responsive Jekyll theme for academics

🎓 无需编写任何代码即可轻松创建漂亮的学术网站 Easily create a beautiful academic résumé or educational website using Hugo and GitHub. No code.

A boutique Jekyll theme for hackers, nerds, and academics

🌐 Jekyll is a blog-aware static site generator in Ruby

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification

A GPU accelerated error-bounded lossy compression for scientific data.

OpenHPC Integration, Packaging, and Test Repo

Build an OpenHPC test cluster in one command using Vagrant and VirtualBox.

An optimized CUDA SDOT(Single Floating-Point DOT Product) kernel on NVIDIA Turing GPUs. Better performance than the cuBLAS kernel.