The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

SDK for developing enclaves

Disaggregated serving system for Large Language Models (LLMs).

A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

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

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Where the GPU for the Web work happens!

A latent text-to-image diffusion model

The Julia Programming Language

cuML - RAPIDS Machine Learning Library

cuDF - GPU DataFrame Library

CUDA integration for Python, plus shiny features

CUDA Python: Performance meets Productivity

CGBN: CUDA Accelerated Multiple Precision Arithmetic (Big Num) using Cooperative Groups

A testing framework for Cobol applications

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

LLM training code for Databricks foundation models

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

CUDA accelerated(X) Multi-Precision library

Handy toolbelt to deal nicely with offline/online connectivity in a React Native app. Smooth redux integration ✈️

Source code for the X Recommendation Algorithm

Locally run an Instruction-Tuned Chat-Style LLM

The anytime MaxSAT solver Loandra

oneAPI Threading Building Blocks (oneTBB)

A toolkit for SAT-based prototyping in Python

UWrMaxSat is a relatively new MiniSat+-based solver participating in MaxSAT Evaluation 2019, where it ranked second places in both main tracks (weighted and unweighted). In MaxSAT Evaluation 2020 …

hping network tool

A REST API for Caffe using Docker and Go

gophersat, a SAT solver in Go