Popular GitHub Repositories for Cuda Kernels

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

SGLang is a fast serving framework for large language models and vision language models.

kaldi-asr/kaldi is the official location of the Kaldi project.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Containers for machine learning

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

CUDA Templates for Linear Algebra Subroutines

Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

A flexible framework of neural networks for deep learning

Efficient Triton Kernels for LLM Training

cuML - RAPIDS Machine Learning Library

A PyTorch Library for Accelerating 3D Deep Learning Research

A collection of important graph embedding, classification and representation learning papers with implementations.

Tengine is a lite, high performance, modular inference engine for embedded device

Lightning fast C++/CUDA neural network framework

Fast inference engine for Transformer models

Supercharge Your LLM with the Fastest KV Cache Layer

FlashInfer: Kernel Library for LLM Serving