OneDiff: An out-of-the-box acceleration library for diffusion models.

CUDA Kernel Benchmarking Library

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

Test suite for probing the numerical behavior of NVIDIA tensor cores

compiler learning resources collect.

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

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

OpenCL extension for csmith.

A CUDA compiler fuzzer

A primitive library for neural network

Optimized primitives for collective multi-GPU communication

cppreference.com html archive converter to microsoft help (for Visual Studio 2012+) and chm help (for Windows)

Csmith, a random generator of C programs

A list of tutorials, paper, talks, and open-source projects for emerging compiler and architecture

First-Class GPU Resource Management: Device Drivers, Runtimes, and CUDA Compilers for Nouveau.

CUDA Templates for Linear Algebra Subroutines

Python bindings for FFmpeg - with complex filtering support

This repository is a home to Intel® Deep Learning Streamer (Intel® DL Streamer) Pipeline Framework. Pipeline Framework is a streaming media analytics framework, based on GStreamer* multimedia frame…

A library for efficient similarity search and clustering of dense vectors.

《Linux/Unix系统编程手册》笔记

Khronos Vulkan, OpenGL, and OpenGL ES Conformance Tests

SPIR-V specs

The WebRTC project

OpenCL for Rust

OpenCL for Rust

Rust tools for OpenCL and GPU management.

zk-SNARK library