Integrating multiple operators (iDMA + Cache) onto cadence/vision on a chosen, stable, ExecuTorch branch.

[cad-rlc]

Summary

Following operators integrated:

1. Softmax (iDMA + Cache)
2. Maxpool (Cache based)
3. Add (w/o broadcasting) (iDMA + Cache)
4. ReLu (iDMA + Cache)
5. Quantize (float to int8) (iDMA + Cache)
6. Dequantize (int8 to float) (iDMA + Cache)

Test plan

Commands used for testing can be found in backends/cadence/build_cadence_vision.sh

P.S. - This is based on an older version of ExecuTorch, which we have treated as a stable branch.

@mcremon-meta @hsharma35 @zonglinpengmeta

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17248

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 6303d7a with merge base da6306f ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.