berkus
/
ANE
mirror of https://github.com/maderix/ANE.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Revise README for clarity and additional details 

Updated README to clarify implementation details and added NEON CPU decode.
This commit is contained in:
gigantic 2026-03-02 13:39:26 -08:00 committed by GitHub
parent 40a5384074
commit 70bfa4e54e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -8,11 +8,9 @@ GPT2 had more soul in it's theoretical pinky finger than all of us combined.
But I digress..
Training neural networks directly on Apple's Neural Engine (ANE) via reverse-engineered private APIs. No CoreML training APIs, no Metal, no GPU — pure ANE compute.
## What This Is
A from-scratch implementation of transformer training (forward + backward pass) running on the ANE in Apple Silicon. The ANE is a 15.8 TFLOPS (M4) inference accelerator that Apple does not expose for training. This project reverse-engineers the `_ANEClient` / `_ANECompiler` private APIs and the MIL (Model Intermediate Language) format to run custom compute graphs — including backpropagation — directly on ANE hardware.
A from-scratch implementation of transformer training (forward + backward pass) running on the ANE in Apple Silicon with NEON cpu decode.
I forked diz shit and need to write out everything different so stay tuned.
@ -23,3 +21,4 @@ This project is independent research into Apple Neural Engine architecture. It u
## License
MIT — see [LICENSE](LICENSE)