Articles, guides, and engineering series by Dhruv Patel.
An in-depth 6-part engineering series exploring what it really takes to build an offline-first, on-device multimodal AI workstation for Android and iOS using Kotlin Multiplatform, C++20 / NDK, llama.cpp, and Google LiteRT.
Why running language models locally matters for privacy, exploring llama.cpp and ARM NEON acceleration, and the realities of moving beyond toy chat boxes.
How a simple 'attach file' button turned into an offline ingestion pipeline for 25+ formats using pure RFC 1951 Deflate and memory-mapped chunks.
Handling the hardest bugs: Android Low Memory Killer (LMK) evictions, GPU driver crashes on Vulkan, thermal throttling, and native lifecycle management.
Integrating on-device diffusion models with Google LiteRT and Bonsai Image Ternary 4B, managing dynamic feature delivery, and preventing mobile GPU overheating.
Refactoring a monolithic mobile app into a multi-module MVI platform with clean offline boundaries, strict state stores, and zero cloud leaks.
Engineering dual-model speculative drafting for 2x decoding speed, isolating GPU driver segmentation faults in a native fork() sandbox, and streaming fault tolerance.
