Stars
Mobile-Agent: The Powerful Mobile Device Operation Assistant Family
A modern model graph visualizer and debugger
A UI-Focused Agent for Windows OS Interaction.
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Tool for visual profiling Core ML models, compatible with both package and compiled versions, including reasons for unsupported operations on the Neural Engine
Supporting PyTorch models with the Google AI Edge TFLite runtime.
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
we want to create a repo to illustrate usage of transformers in chinese
A high-throughput and memory-efficient inference and serving engine for LLMs
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
a quick and dirty little program to convert Apple CoreML model to ANE hwx file
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
程序员延寿指南 | A programmer's guide to live longer
MediaTek's TFLite delegate
Everything we actually know about the Apple Neural Engine (ANE)
Apollo notes (Apollo学习笔记) - Apollo learning notes for beginners.
This is the source code of the feasibility study for Autoware architecture proposal.
Cross-platform, customizable ML solutions for live and streaming media.
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown
https://github.com/benmahr/RenZhengfei
"Multi-Level Intermediate Representation" Compiler Infrastructure
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Super fast sftp/ftp extension for VS Code
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training