cuda

Best practices & guides on how to write distributed pytorch training code

Numerical linear algebra software package

High-Performance Cross-Platform Monte Carlo Renderer Based on LuisaCompute

Optimizing AlphaFold Training and Inference on GPU Clusters

AutoDock for GPUs and other accelerators

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

An app and guide to easily configure Windows, Linux, MacOS, Google TV, Stremio, Home Assistant and more (including WSL2, GPU drivers & development tools). Improve your UX & productivity.

Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

Minimum-distortion embedding with PyTorch

DaCe - Data Centric Parallel Programming

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.

Radar Simulator built with Python and C++

A single-header C++ library for simplifying the use of CUDA Runtime Compilation (NVRTC).

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

An open collection of methodologies to help with successful training of large language models.

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

LLM algorithm practice lab with theory, solutions, and test cases.《大模型算法与系统教程》面向大模型入门到进阶的算法实战教程，覆盖原理讲解、答案解析、测试用例与 CUDA/Triton 实战。

Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work

Image-processing software for cryo-electron microscopy

A Slurm cluster using docker-compose

package cu provides an idiomatic interface to the CUDA Driver API.

a reimplementation of Holistically-Nested Edge Detection in PyTorch

INSTA - Instant Volumetric Head Avatars [CVPR2023]

Data visualisation and ray tracing in Python based on OptiX 9.1 framework.

Docker Image for Ubuntu Desktop which support HW GPU accelerated GUI apps. you can access the Container with ssh or remote desktop, just like Cloud VM.

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS