Skip to content

NXP backend: Add support for softmax with the new Neutron flow.#19739

Open
irtrukhina wants to merge 6 commits into
pytorch:mainfrom
nxp-upstream:feature/EIEX-728_revisit_softmax_support
Open

NXP backend: Add support for softmax with the new Neutron flow.#19739
irtrukhina wants to merge 6 commits into
pytorch:mainfrom
nxp-upstream:feature/EIEX-728_revisit_softmax_support

Conversation

@irtrukhina

@irtrukhina irtrukhina commented May 22, 2026

Copy link
Copy Markdown
Contributor

Summary

Add support for the softmax to the Neutron backend using the new Neutron MLIR flow. Add new tests and update old tests for the softmax as well.

Test plan

New tests are included in the PR.

cc @robert-kalmar @JakeStevens @digantdesai @rascani

@irtrukhina irtrukhina requested a review from robert-kalmar as a code owner May 22, 2026 08:08
@pytorch-bot

pytorch-bot Bot commented May 22, 2026

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19739

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

❌ 1 Cancelled Job

As of commit f504223 with merge base 2759ef1 (image):

CANCELLED JOB - The following job was cancelled. Please retry:

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

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 22, 2026
@linux-foundation-easycla

linux-foundation-easycla Bot commented May 22, 2026

Copy link
Copy Markdown

CLA Not Signed

@robert-kalmar robert-kalmar added module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate labels May 22, 2026
Comment thread backends/nxp/tests/generic_tests/test_integration.py Outdated
Comment thread backends/nxp/tests/ir/converter/node_converter/test_softmax_converter.py Outdated
Comment thread backends/nxp/tests/ir/edge_passes/test_remove_io_quant_ops_pass.py Outdated
@irtrukhina irtrukhina force-pushed the feature/EIEX-728_revisit_softmax_support branch from 154ffff to 56a1296 Compare June 1, 2026 16:09
Comment thread backends/nxp/tests/ir/converter/node_converter/test_softmax_converter.py Outdated
@irtrukhina irtrukhina force-pushed the feature/EIEX-728_revisit_softmax_support branch from c8324ed to c122421 Compare June 4, 2026 08:54
Comment thread backends/nxp/tests/ir/converter/node_converter/test_softmax_converter.py Outdated
1. Input and Output must be INT8/UINT8
2. Channels <= 2040
3. Total spatial size (H*W) <= 4096
3. Total spatial size <= 4096

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: As far as I know total spatial size is not a universally known term. Before your change, it was supposed to represent H*W, whereas now it means N*H*W. Please keep the explicit definition here.

@MartinPavella

Copy link
Copy Markdown
Collaborator

Please take a look at the canceled pull / unittest-nxp-neutron / linux-job (pull_request). Otherwise, LGTM

@irtrukhina irtrukhina force-pushed the feature/EIEX-728_revisit_softmax_support branch from 502f045 to f504223 Compare June 9, 2026 08:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants