christophe0606/MLHelium

TinyLlama on Cortex-M55 using CMSIS-DSP and Helium vector instructions

28
/ 100
Experimental

This project helps embedded systems engineers and firmware developers implement small machine learning models on Arm Cortex-M55 microcontrollers. It provides a way to integrate neural network kernels, optimized using Helium vector instructions and CMSIS-DSP, directly into C code. The output is a highly efficient, custom-built ML inference solution for resource-constrained edge devices.

No commits in the last 6 months.

Use this if you need to run very small, simple machine learning models on Cortex-M55 microcontrollers with maximum efficiency and minimal dependencies.

Not ideal if you require automatic model conversion from frameworks like TensorFlow or PyTorch, or need support for fully quantized kernels and Arm NPUs.

embedded-development firmware-engineering edge-ai microcontroller-programming resource-constrained-ml
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

C

License

Apache-2.0

Last pushed

Oct 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/christophe0606/MLHelium"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.