Machine Learning Systems

Production Android AI with ExecuTorch 1.0 - Deploy PyTorch models to mobile with NPU acceleration and 50KB footprint

LLM inference on mobile via Capacitor — run quantized GGUF models on-device

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

GGUF/llama.cpp inference and chat runtime for Dust — iOS/macOS with Metal GPU

Device Unified Serving Toolkit — central hub for the Dust on-device ML ecosystem

📱 Optimized ML for edge devices. Showcasing efficient model deployment, GPU-CPU memory transfer optimization, and real-world edge AI applications. 🤖

Standalone ONNX runtime session management and preprocessing for Dust — iOS/macOS

 INT8 quantization of MobileNetV2 for learning and production-oriented iOS mobile inference.

DustCore contract types and interfaces for on-device ML — pure Kotlin/JVM

Model download and serving orchestration for Dust — Capacitor bridge

On-device text embedding generation for iOS and Android via Capacitor

Android ONNX runtime session management and preprocessing for Dust

Claude Code skill for Google LiteRT - on-device AI/ML deployment framework

DustCore contract types and protocols for on-device ML — pure Swift

Android GGUF/llama.cpp inference and chat runtime with JNI bindings

Android ML model server — download management, session caching, accelerator probing

Standalone tokenizers and embedding runtime primitives for on-device text embeddings

 magnitude-based pruning of MobileNetV2 for learning and production-oriented iOS mobile inference.

Standalone model server business logic for iOS — download, caching, accelerator probing