Building EdgeMind: Experimenting with LLM Inference on Android
Edge MLOps experiments: implementing Phi-3 mini on Android from scratch with NNAPI acceleration, custom tokenization, and KV caching
Thoughts on AI, mobile development, and building things. I write to share what I'm learning and thinking about.
Edge MLOps experiments: implementing Phi-3 mini on Android from scratch with NNAPI acceleration, custom tokenization, and KV caching
Insights from founding and leading an open source team building digital tools for animal shelters
Deep dive into the architecture decisions and implementation details of CountIn, a real-time occupancy tracking app