Stars
Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.
🚀Lightweight Large language model automation and Autonomous Language Agents development framework. Build your LLM Agent Application in a pythonic way!
Transformer related optimization, including BERT, GPT
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT
Making large AI models cheaper, faster and more accessible
NVIDIA Linux open GPU kernel module source
Neo-AI-DLR is a common runtime for machine learning models compiled by AWS SageMaker Neo, TVM, or TreeLite.
LightSeq: A High Performance Library for Sequence Processing and Generation
Explore the Capabilities of the TensorRT Platform
Tensors and Dynamic neural networks in Python with strong GPU acceleration
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶
makefile 交叉编译 libmace.a，并能在嵌入式端调用GPU来跑深度学习模型
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …
High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.
A high-performance and stable proxy for MySQL, it is developed by Qihoo's DBA and infrastructure team
the awesome qt210 dev-board--samsung s5pv210 based
the awesome qt210 dev-board--samsung s5pv210 based
the awesome qt210 dev-board--samsung s5pv210 based
the awesome qt210 dev-board--samsung s5pv210 based