Blog
Lessons learned while building operating systems, inference runtimes, simulators and research testbeds for constrained hardware. New articles arrive by RSS.
Five Raspberry Pi 4 boards, an edge server and the NNPM web application: how the experimental platform of my PhD runs a partitioned-inference experiment end to end, under controlled network and compute conditions, and how anyone can rerun it.
How I picked my first issues, what maintainers asked for, and the habits that stuck after ten pull requests to a large RTOS project.
What goes wrong when a neural network is bolted onto a scheduler built for control loops, and the design decisions behind SynapticOS.
A small language model does not fit one edge device. Lessons from a WiFi testbed, a simulator and two papers on partitioning inference.
Why a microcontroller inference library should never touch the heap, and how a static arena, INT8 arithmetic and a graph runtime fit in under 50 KB.