Skip to content

Fix missing import in Gemma2-2B model #16684

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
mergennachin merged 1 commit into from
Jan 17, 2026
Merged

Fix missing import in Gemma2-2B model #16684

mergennachin merged 1 commit into from
Jan 17, 2026

Conversation

@mergennachin
Copy link
Contributor

@mergennachin mergennachin commented Jan 17, 2026 •
edited
Loading

Follow-up to #16624 where it didn't git add the necessary folder examples/models/gemma2. As a result, it didn't have the necessary config and conversion script when landing the PR

Our CI is timing out due to

  # test_qnn_delegate.py:6430-6433
  p = subprocess.Popen(cmds, stdout=subprocess.DEVNULL)
  with Listener((self.ip, self.port)) as listener:
      conn = listener.accept()  # ← BLOCKS forever waiting for connection where it already had failed with not found module
      p.communicate()

https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=test-static-llama-qnn-linux&mergeEphemeralLF=true

@mergennachin
Fix missing import in Gemma2-2B model
a5fc1c8 
It didn't add the necessary config and conversion script when landing the PR

As a result, our CI is timing out due to

```
  # test_qnn_delegate.py:6430-6433
  p = subprocess.Popen(cmds, stdout=subprocess.DEVNULL)
  with Listener((self.ip, self.port)) as listener:
      conn = listener.accept()  # ← BLOCKS forever waiting for connection
      p.communicate()
```

https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=test-static-llama-qnn-linux&mergeEphemeralLF=true
@mergennachin mergennachin requested a review from lucylq as a code owner January 17, 2026 16:10
Copilot AI review requested due to automatic review settings January 17, 2026 16:10
@pytorch-bot
Copy link

pytorch-bot bot commented Jan 17, 2026 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16684

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

⏳ No Failures, 19 Pending

As of commit a5fc1c8 with merge base af69d08 (image):
💚 Looks good so far! There are no failures yet. 💚

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 Jan 17, 2026
@mergennachin
Copy link
Contributor Author

mergennachin commented Jan 17, 2026 •
edited
Loading

Follow-up to #16624 cc @jethroqti

@mergennachin mergennachin mentioned this pull request Jan 17, 2026
Merged
Copilot AI reviewed Jan 17, 2026
View reviewed changes
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR adds missing files for the Gemma2-2B model that were not included in the original PR. These files are essential for model weight conversion and configuration, and their absence was causing CI timeouts during QNN delegate testing.

Changes:

  • Added weight conversion script with Gemma2-specific weight mappings for transformer parameter conversion
  • Added 2B model configuration with Gemma2-specific settings (softcapping, sliding window, layer types)
  • Added module initialization with Gemma2Model class definition and exported utilities

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File Description
examples/models/gemma2/convert_weights.py Implements weight conversion from HuggingFace checkpoints to ExecuTorch format with Gemma2-specific layer normalizations
examples/models/gemma2/config/2b_config.json Defines Gemma2-2B model architecture parameters including attention/logit softcapping and sliding window configuration
examples/models/gemma2/init.py Exports Gemma2Model class and convert_weights utility for external use

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot AI reviewed Jan 17, 2026
View reviewed changes
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@mergennachin mergennachin merged commit 7492d0d into main Jan 17, 2026
181 of 183 checks passed
@mergennachin mergennachin deleted the debug_qnn branch January 17, 2026 16:52
@jethroqti
Copy link
Contributor

jethroqti commented Jan 18, 2026

@pytorchbot label "release notes: qualcomm"

@pytorch-bot pytorch-bot bot added the release notes: qualcomm Changes to the Qualcomm backend delegate label Jan 18, 2026
@jethroqti
Copy link
Contributor

jethroqti commented Jan 18, 2026

Added Gemma2 data.
cc @cccclai @haowhsu-quic @rascani

@DannyYuyang-quic DannyYuyang-quic mentioned this pull request Jan 19, 2026
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Copilot code review Copilot Copilot left review comments

@rascani rascani rascani approved these changes

@lucylq lucylq Awaiting requested review from lucylq lucylq is a code owner

@cccclai cccclai Awaiting requested review from cccclai

@haowhsu-quic haowhsu-quic Awaiting requested review from haowhsu-quic

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. release notes: qualcomm Changes to the Qualcomm backend delegate

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@mergennachin @jethroqti @rascani