📍 Hangzhou, China | 🤖 On-Device AI & LLM Enthusiast | 🏗️ MNN Core Developer
Inference Engine Expert at Alibaba (Taotian Group), core architect of MNN. Making LLMs run fast on edge devices.
- 🧠 MNN - Blazing fast, lightweight deep learning inference engine (13k+ stars)
- 💬 mnn-llm - LLM deployment on mobile devices
- 🔗 onnx-llm - ONNX-based LLM inference
- 📦 llm-export - Export LLM models to ONNX format for cross-platform deployment
- 📝 jinja.cpp - Single-header C++11 Jinja2 engine for LLM chat templates
- 🔤 tokenizer.cpp - Lightweight C++ library for LLM tokenization, HuggingFace compatible
- 🎤 mnn-asr - MNN-based Automatic Speech Recognition demo
- 🔊 mnn-tts - MNN-based Text-to-Speech demo
- 🎯 mnn-yolo - MNN-based YOLO object detection demo
- ✂️ mnn-segment-anything - MNN-based Segment Anything demo
- 📱 mnn-mobilenet - MNN-based MobileNet classification demo
- 🎨 mnn-stable-diffusion - MNN-based Stable Diffusion image generation
- 🖼️ clawdicons - Icon collection
- 🧪 llm-lab - LLM experiments and research notes
📖 Tech Blog | ⭐ Follow me on GitHub