Skip to content

[DO NOT MERGE] Copy of 2384#2385

Draft
jambayk wants to merge 1 commit intomainfrom
intel/nncf-external
Draft

[DO NOT MERGE] Copy of 2384#2385
jambayk wants to merge 1 commit intomainfrom
intel/nncf-external

Conversation

@jambayk
Copy link
Copy Markdown
Contributor

@jambayk jambayk commented Apr 6, 2026

Add change to auto-detect ONNX external data files in NNCF compression pass.
If an ONNX model is locally sourced, the ONNXModelHandler points to just the .onnx file. This means that the EXTERNAL_DATA_DIR isn't set in AdvancedCompressionParameters, leading to NNCF failing to find the model weights.
This commit fixes that and allows auto-detecting the presence of an external data file, and will pass this path to NNCF AdvancedCompressionParameters if not already set manually with local sourcing or if chained with another pass that produces an ONNX model with external data

  • Add unit tests for this change.
  • Make sure all tests can pass.
  • Update documents if necessary.
  • Lint and apply fixes to your code by running lintrunner -a
  • Is this a user-facing change? If yes, give a description of this change to be included in the release notes.

Describe your changes

Checklist before requesting a review

  • Add unit tests for this change.
  • Make sure all tests can pass.
  • Update documents if necessary.
  • Lint and apply fixes to your code by running lintrunner -a
  • Is this a user-facing change? If yes, give a description of this change to be included in the release notes.

(Optional) Issue link

Add change to auto-detect ONNX external data files in NNCF compression
pass.
If an ONNX model is locally sourced, the ONNXModelHandler points to just
the .onnx file. This means that the EXTERNAL_DATA_DIR isn't set in
AdvancedCompressionParameters, leading to NNCF failing to find the model
weights.
This commit fixes that and allows auto-detecting the presence of an
external data file, and will pass this path to NNCF
AdvancedCompressionParameters if not already set manually with local
sourcing or if chained with another pass that produces an ONNX model
with external data

- [x] Add unit tests for this change.
- [x] Make sure all tests can pass.
- [ ] Update documents if necessary.
- [x] Lint and apply fixes to your code by running `lintrunner -a`
- [ ] Is this a user-facing change? If yes, give a description of this
change to be included in the release notes.

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants