# PaddlePaddle/Paddle-Lite

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）

Repository: https://github.com/PaddlePaddle/Paddle-Lite
Canonical: https://ross.abutalabs.com/products/paddle-lite
Homepage: https://www.paddlepaddle.org.cn/lite
Language: C++
License: Apache-2.0
License Family: permissive
Topics: mobile, deep-learning, neural-network, arm, mdl, baidu, embedded, mali, fpga, mobile-deep-learning
Last push: 2026-04-27T09:16:13+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 8, longevity 100
- inputs: {"age_days": 3269, "days_push": 128, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7273, forks 1619 (observed 2026-08-28T04:09:57.960961+00:00)

## What it is
Paddle Lite is a high-performance, lightweight deep learning inference engine from Baidu's PaddlePaddle ecosystem, designed for mobile, embedded, and edge devices. It optimizes models via quantization, kernel selection, and graph fusion, and provides C++, Java, and Python APIs for on-device deployment.

## Use cases
- deploy a deep learning model on Android or iOS
- run neural network inference on embedded ARM devices
- optimize and quantize a PaddlePaddle model for mobile
- run image classification or object detection on-device
- convert TensorFlow or PyTorch models for edge inference
- accelerate inference on mobile GPU or FPGA hardware

## When to choose
- you need fast on-device inference on Android, iOS, or embedded Linux
- your models come from PaddlePaddle or can be converted via X2Paddle
- you need quantization and graph optimization for resource-constrained devices

## When to avoid
- you need training, not inference - use full PaddlePaddle or PyTorch
- you primarily target server/cloud GPUs rather than mobile and edge
- you need broad non-Paddle model format support without conversion

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, gpu-computing
- domain: deep-learning, mobile-development, embedded-systems, machine-learning
- platform: windows, cpp, python, embedded
- tags: inference-engine, edge-computing, model-optimization, quantization, on-device-ai, paddlepaddle, android, ios, linux, macos, arm

## Member repositories
- PaddlePaddle/Paddle-Lite (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:57.960961+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:38:54.985476+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/Paddle-Lite (fetched 2026-08-28T04:09:57.960961+00:00, sha d10a98ea0c7f)
  - homepage: https://www.paddlepaddle.org.cn/lite (fetched 2026-08-29T08:34:17.768706+00:00, sha 9fc4afe5db6d)
- Data as of 2026-08-30T08:39:29.467469+00:00.