The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

A throughput-oriented high-performance serving framework for LLMs

Nvidia Instruction Set Specification Generator

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

llama3 implementation one matrix multiplication at a time

System design patterns for machine learning

High performance server-side application framework

Safe rust wrapper around CUDA toolkit

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Minimalist ML framework for Rust

High performance containers and utilities for concurrent and asynchronous programming

Asynchronous Programming in Rust, published by Packt

High-level, optionally asynchronous Rust bindings to llama.cpp

A heap memory profiler for Linux

Code samples for the book Patterns in C

“Zero setup” cross compilation and “cross testing” of Rust crates

ix package manager

Literature references for “Designing Data-Intensive Applications”

Xray, Penetrates Everything. Also the best v2ray-core, with XTLS support. Fully compatible configuration.

HTTP and WebSocket built on Boost.Asio in C++11

High level Lua 5.4/5.3/5.2/5.1 (including LuaJIT) and Roblox Luau bindings to Rust with async/await support

Boost.org asio module

Find out what takes most of the space in your executable.

Modern concurrency for C++. Tasks, executors, timers and C++20 coroutines to rule them all

🚧 (Alpha stage software) Edit files, run programs, and work with LSP on a remote machine from the comfort of your local environment 🚧

Distributed SQL database in Rust, written as an educational project

Fork of std::sync::Arc with lots of utilities useful for FFI

GNU toolchain for RISC-V, including GCC

Xv6 for RISC-V