Stars
Tile primitives for speedy kernels
A Large-Scale Computation Graph Database for Tensor Compiler Research
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient Multi-head Latent Attention Kernels
MoBA: Mixture of Block Attention for Long-Context LLMs
[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high …
PyTorch code and models for the DINOv2 self-supervised learning method.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Painter & SegGPT Series: Vision Foundation Models from BAAI
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, RT-DETR, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv10, YOLO11, YOLOX, YOLOv5u, YOLOv7u, YOLOv6Lite, RTMDet and so on. 🚀🚀🚀
A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
🚀🚀🚀 YOLOv5 of PaddleDetection, Paddle implementation of YOLOv5
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
使用ONNXRuntime部署PP-YOLOE目标检测，支持PP-YOLOE-s、PP-YOLOE-m、PP-YOLOE-l、PP-YOLOE-x四种结构，包含C++和Python两个版本的程序
NVIDIA Linux open GPU kernel module source
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
分享paddledetection导出的预测文件，Share the inference model exported by PaddleDetection
PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.