Skip to content

Refactor autoregressive model tests#1486

Merged
pstjohn merged 2 commits intoNVIDIA:mainfrom
pstjohn:pstjohn/refactor-generation-tests
Mar 2, 2026
Merged

Refactor autoregressive model tests#1486
pstjohn merged 2 commits intoNVIDIA:mainfrom
pstjohn:pstjohn/refactor-generation-tests

Conversation

@pstjohn
Copy link
Collaborator

@pstjohn pstjohn commented Feb 28, 2026

Moves shared auto-regressive model tests to modeling_common, making it easier to add new auto-regressive models

Summary by CodeRabbit

  • Tests

    • Added generation tests with KV-cache support across model architectures (ESM2, LLaMA3, Mixtral), including batched and beam search variants.
    • Expanded test infrastructure to support flexible configuration overrides in quantized model tests.
  • Bug Fixes

    • Improved numerical stability in Mixtral by adjusting tensor dtype handling for expert routing operations.
  • Refactor

    • Consolidated generation test implementations across models into shared base test class to reduce duplication.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Feb 28, 2026

Important

Review skipped

Auto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • ✅ Review completed - (🔄 Check again to review again)
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Comment @coderabbitai help to get the list of available commands and usage tips.

@pstjohn pstjohn mentioned this pull request Feb 28, 2026
Signed-off-by: Peter St. John <pstjohn@nvidia.com>
@pstjohn pstjohn force-pushed the pstjohn/refactor-generation-tests branch from 2dad2a4 to ef39689 Compare February 28, 2026 15:54
Signed-off-by: Peter St. John <pstjohn@nvidia.com>
Copy link
Collaborator

@jomitchellnv jomitchellnv left a comment

Choose a reason for hiding this comment

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

lgtm

@pstjohn pstjohn added this pull request to the merge queue Mar 2, 2026
Merged via the queue into NVIDIA:main with commit beec19f Mar 2, 2026
17 checks passed
@pstjohn pstjohn deleted the pstjohn/refactor-generation-tests branch March 2, 2026 21:13
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