llmedge
Android runtime that runs LLMs, diffusion, and speech models locally on real phones. One Kotlin API over llama.cpp, stable-diffusion.cpp, whisper.cpp, and ONNX.
01 · selected work
A 6DOF flight sim and autopilot in Rust. A quadrotor and a fixed-wing, flown by complementary/MEKF/INS estimators and PID/LQR control over a 1/1000-scale Earth.
Local image-generation system. Pipeline core, queueing server, browser UI, tuned with Xformers, BFloat16, WaveSpeed, and Stable-Fast.
Offline-first Android reader for web chapters, PDF, EPUB, and manga, with on-device chapter summaries through llmedge.
02 · about
My first real project was an autonomous submarine. The hard part was the Kalman filter, getting a steady heading out of noisy IMU data.
Now it's edge AI, running models locally on phones and embedded boards. I want to take that into automotive or aerospace next.
03 · stack
languages & systems
where the time goes
ai & inference
the model side
embedded & signal
what brought me here
04 · index