Skip to content

[model] fix: use hf_config to check whether model is dense#4414

Merged
yaoyu-33 merged 2 commits into
NVIDIA-NeMo:mainfrom
pavelgein:fix_gemma4_dense_model
Jun 25, 2026
Merged

[model] fix: use hf_config to check whether model is dense#4414
yaoyu-33 merged 2 commits into
NVIDIA-NeMo:mainfrom
pavelgein:fix_gemma4_dense_model

Conversation

@pavelgein

Copy link
Copy Markdown
Contributor

What does this PR do ?

Using hf config to check whether model is dense or not

Changelog

  • Add specific line by line info of high level changes in this PR.

GitHub Actions CI

See the CI section in the Contributing doc for how to trigger the CI. A Nvidia developer will need to approve and trigger the CI for external contributors.

Before your PR is "Ready for review"

Pre checks:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?
  • Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
    • Reviewer: Does the PR have correct import guards for all optional libraries?

If you haven't finished some of the above items you can still open "Draft" PR.

Additional Information

Signed-off-by: Pavel Gein <pavel.gein@gmail.com>
@copy-pr-bot

copy-pr-bot Bot commented Jun 18, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@pavelgein

Copy link
Copy Markdown
Contributor Author

The problem is that bridge recreated every time, so _is_dense attribute is not set

yaoyu-33
yaoyu-33 previously approved these changes Jun 19, 2026
Signed-off-by: yaoyu-33 <yaoyu.094@gmail.com>
@yaoyu-33

Copy link
Copy Markdown
Contributor

/ok to test 2573a5d

@yaoyu-33 yaoyu-33 enabled auto-merge (squash) June 21, 2026 03:46
@yaoyu-33 yaoyu-33 added area:model Model implementations and HF bridge logic bug Something isn't working needs-review PR is ready for code review and waiting on a reviewer labels Jun 22, 2026
@yaoyu-33 yaoyu-33 merged commit 394a7cf into NVIDIA-NeMo:main Jun 25, 2026
76 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area:model Model implementations and HF bridge logic bug Something isn't working community-request needs-review PR is ready for code review and waiting on a reviewer

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants