pytorch / pytorch/executorch

Publish performance baselines and establish KPI tracking for Cortex-M

Open
#17,650 0 comments 0 reactions 1 assignee View on GitHub

@rascani is already working on this.

Since Feb 23, 2026.

module: microcontrollers partner: arm
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

Measure and publish performance baselines for ExecuTorch with CMSIS-NN on TinyML benchmark models and Cortex-M targets. Establish ongoing KPI tracking to detect regressions against those baselines over time.

  • Latency and memory (flash + RAM) baselines established for MV2 and KWS on M55 and M33
  • Results published in documentation or blog
  • Gaps identified and tracked as follow-up issues

cc @digantdesai @SS-JIA @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @psiddh @AdrianLundell

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.