#61 · Primary category： Inference & Local Deploy
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）
Project last updated：04/27/26
GitHub Stars
7.3K
Forks
1.6K
Contributors
193
License
Apache-2.0
Why we included this project
Paddle-Lite is an inference runtime built for phones, embedded boards, and other edge hardware. It runs models trained in PaddlePaddle directly, and models from PyTorch, TensorFlow, or Caffe can be converted with the companion X2Paddle tool. An optimization step quantizes and fuses the graph before deployment, which keeps the model small and fast when memory and battery are limited. The engine covers ARM CPUs, GPUs via OpenCL and Metal, and NPUs from Huawei, Qualcomm, MediaTek, Cambricon, and others. C++, Java, and Python APIs support Android, iOS, embedded Linux, and x86, with demos for common tasks like classification and detection. Baidu uses it in production internally, and it has supported external users and enterprises as well.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.