Title here
Summary here
Tinyml
Compile Once, Run Anywhere
Your model rarely picks its chip, and it may have to run on several. One TiGrIS plan produces identical output, down to the bit, across three different Cortex-M cores.
July 23, 2026 in Deep Dives9 minutes
Static Memory Planning for Embedded Neural Network Inference
Peak working memory depends on the execution schedule and allocation, so the schedule can be optimized ahead of time and executed with bounded runtime arenas.
June 11, 2026 in Deep Dives9 minutes