MNN

MNN is an open-source, lightweight, high-performance inference engine developed by Alibaba, supporting various mainstream model formats.

ChineseSelectionProgrammingDeep LearningInference Engine

Visit

MNN is a deep learning inference engine open-sourced by Alibaba's Taobao technology platform, supporting popular model formats such as TensorFlow, Caffe, and ONNX, while being compatible with commonly used networks like CNN, RNN, and GAN. It achieves exceptional optimization of operator performance and fully supports CPU, GPU, and NPU, maximizing device computing power and widely applied in over 70 AI applications within Alibaba. MNN is recognized for its high performance, ease of use, and versatility, aiming to lower the threshold for AI deployment and promote edge intelligence development.

Product Finder

Product Submit

AI Models Finder

MCP Servers

MCP Client

MCP Inspector

Case Tutorials

Latest AI News

AI Daily Brief

MNN

MNN Visit Over Time

MNN Visit Trend

MNN Visit Geography

MNN Traffic Sources

MNN Alternatives

Understanding Deep Learning — Deep understanding of the principles and applications of deep learning

MNN — MNN is an open-source, lightweight, high-performance inference engine developed by Alibaba, supporting various mainstream model formats.

AI By Doing: Hands-On Artificial Intelligence — An introductory tutorial website for artificial intelligence, providing comprehensive knowledge of machine learning and deep learning.

Cerebras Inference — AI instant inference solution with world-leading speed.

Aphrodite Engine — PygmalionAI's large-scale inference engine

VAST Data Platform — A data platform built for deep learning and artificial intelligence

PowerInfer — High-speed large language model local deployment inference engine

Infini-Megrez — Multimodal understanding model for edge applications, enabling intelligent edge solutions through hardware-software collaboration.

Blaize — Unlocking the potential of artificial intelligence in edge computing

Huginn-0125 — Huginn-0125 is a latent variable recurrent deep model with 3.5 billion parameters, excelling in inference and code generation.

Unity Sentis — Unity Deep Learning Inference Library

AI ChatGPT Search Engine - GPT for Edge — Displays ChatGPT's answers both within the search engine results and in a pop-up window.

Neuton TinyML — Provides no-code artificial intelligence for edge devices.

SIVIA Artificial Intelligence Technology Open Platform — 3D Digital products and services based on deep learning.

cog-flux — Cog inference engine for FLUX models

Trieve Vector Inference — Rapid on-premises vector inference solution

gemma.cpp — The lightweight C++ inference engine for Google's Gemma model

xinsir — Deep Learning, Representation Learning, Fine-Grained Classification

TFLearn — Advanced API simplifies TensorFlow deep learning

AudioCraft — A deep learning library for audio processing and generation.

DiffusionKit — An inference tool for running diffusion models on Apple silicon.

Fathom 2.0 — One-stop deep learning solution

AXLearn — A unified deep learning training framework.

GraphCast — Deep Learning Weather Prediction Model

Cradl AI — Deep Learning Document Parsing API

Keras — A deep learning API that is simple, flexible, and powerful.

SD3-Controlnet-Canny — A deep learning model used for image generation.

LLM Compiler-7b — An advanced large language model for code optimization and compiler inference.

Microsoft Cognitive Toolkit — An open-source, distributed deep learning tool

ML-YouTube-Courses — Explore the latest machine learning/Artificial Intelligence courses on YouTube