Lists (10)
Stars
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Productive, portable, and performant GPU programming in Python.
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
ncnn is a high-performance neural network inference framework optimized for the mobile platform
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
A distributed, fast open-source graph database featuring horizontal scalability and high availability
Unsupervised text tokenizer for Neural Network-based text generation.
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
oneAPI Deep Neural Network Library (oneDNN)
校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step
LightSeq: A High Performance Library for Sequence Processing and Generation
Tutorial code on how to build your own Deep Learning System in 2k Lines
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.
Distributed LR、 FM model on Parameter Server. FTRL and SGD Optimization Algorithm.
Caffe implementation for dynamic network surgery.
High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph