PyTorch ExecuTorch releases an Arm Cortex-M CPU backend
PyTorch ExecuTorch released an Arm Cortex-M CPU backend — models run on microcontrollers without an Ethos-U NPU through the same PyTorch export and quantization flow
Why it matters
In the team's own measurements, 4 MLPerf Tiny models each ran in 21.5ms or less and under 90KiB of RAM on a single Cortex-M55 core of the Alif Ensemble E8 (the anomaly detection autoencoder in 5.2KiB). The team noted these are not an official MLPerf submission
Source — Primary sources first; secondary reports are labelled “Press”
Officialpytorch.orghttps://pytorch.org/blog/bringing-executorch-to-arm-cortex-m-cpus/Added in Week 42, 2026 · See that week