HIP: C++ Heterogeneous-Compute Interface for Portability

super repo for rocm libraries

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

RDNA-native LLM inference engine in Rust.

The main repository for building Pascal-compatible versions of ML applications and libraries.

A fast high-compression read-only file system for Linux, FreeBSD, macOS and Windows

Achieve state of the art inference performance with modern accelerators on Kubernetes

Kimi Code CLI is your next CLI agent.

Jobs scraper library for LinkedIn, Indeed, Glassdoor, Google, ZipRecruiter & more

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

An open-source AI agent that lives in your terminal.

Flexible I/O Tester

A fast JSON parser/generator for C++ with both SAX/DOM style API

NVIDIA Inference Xfer Library (NIXL)

Supercharge Your LLM with the Fastest KV Cache Layer

Distributed reliable key-value store for the most critical data of a distributed system

The etcd-cpp-apiv3 is a C++ library for etcd's v3 client APIs, i.e., ETCDCTL_API=3.

IOR and mdtest

Magnum IO community repo

NVIDIA GPUDirect Storage Driver

llama.cpp fork with additional SOTA quants and improved performance

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Minimal CLI coding agent by Mistral

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

CUDA Library Samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

LLM inference in C/C++

A lightweight chat terminal-interface for llama.cpp server written in C++ with many features and windows/linux support.