Artificial Neural Engine Machine Learning Library

Port of Facebook's LLaMA model in C/C++

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

MiniCPM on iOS.

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Swift library to work with llama and other large language models.

Cross-platform, customizable ML solutions for live and streaming media.

MiniCPM on Android platform.

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.

GLake: optimizing GPU memory management and IO transmission.

Efficient Training (including pre-training and fine-tuning) for Big Models

Fast and memory-efficient exact attention

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）

Compiler Infrastructure for Neural Networks

Documentations for PaddlePaddle

An experimental open-source attempt to make GPT-4 fully autonomous.

Paddle Distributed Training Examples. 飞桨分布式训练示例 Resnet Bert GPT MOE DataParallel ModelParallel PipelineParallel HybridParallel AutoParallel Zero Sharding Recompute GradientMerge Offload AMP DGC Loc…

Zero-knowledge template library

A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.

CUDA Library Samples

fast zksnark prover

SECOND for KITTI/NuScenes object detection

NVIDIA Linux open GPU kernel module source

Spatial Sparse Convolution Library