Explore Projects
Discover 195 open source projects
Showing 21-40 of 195 projects
numba/numba
NumPy-aware dynamic Python compiler using LLVM, enabling fast, high-performance array and numerical computing.
bigscience-workshop/petals
A distributed system for running large language models (LLMs) on personal devices, enabling faster fine-tuning and inference.
microsoft/napajs
Napa.js is a multi-threaded JavaScript runtime that allows developers to leverage multi-core processors for improved performance.
deepseek-ai/DeepEP
DeepEP is an efficient expert-parallel communication library for CUDA-based applications.
progschj/ThreadPool
A simple C++11 Thread Pool implementation for concurrency and parallelism in C++ applications.
Yeachan-Heo/oh-my-claudecode
A powerful multi-agent orchestration tool for Claude Code that automates the development workflow from idea to working code.
crossbeam-rs/crossbeam
Crossbeam is a Rust library that provides tools for concurrent programming, including data structures and synchronization primitives.
EleutherAI/gpt-neo
An open-source implementation of GPT-2 and GPT-3-style language models using the mesh-tensorflow library.
puma/puma
A Ruby/Rack web server built for parallelism, suitable for backend development.
open-cli-tools/concurrently
Concurrently run multiple commands in the command line, making it easier to manage parallel processes.
automazeio/ccpm
AI-powered coding tools for Claude Code
EleutherAI/gpt-neox
An open-source implementation of large language models with a focus on model parallelism and efficiency.
halide/Halide
A fast, portable data-parallel computation language for image processing and performance optimization.
uxlfoundation/oneTBB
oneAPI Threading Building Blocks (oneTBB) is a C++ library for creating parallel applications using task-based programming.
kingoflolz/mesh-transformer-jax
Transformers built with JAX and Haiku for mesh-based AI applications.
mysticatea/npm-run-all
A CLI tool to run multiple npm-scripts in parallel or sequential for Node.js developers.
google/highway
A performance-portable and length-agnostic SIMD library with runtime dispatch for C++.
LWJGL/lwjgl3
A Java library that provides cross-platform access to native APIs for graphics, audio, parallel computing, and XR development.
xlite-dev/Awesome-LLM-Inference
A curated list of awesome papers and code for optimizing LLM/VLM inference performance
NVIDIA/thrust
A C++ parallel algorithms library that provides high-performance GPU acceleration for scientific computing and data analysis.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.