Skip to content
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.

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

Enable CUDA graphs by default only for transcription #9197

Merged

Conversation

github-actions[bot]
Copy link
Contributor

What does this PR do ?

Temporary disable by default CUDA graphs due to instability with DDP. Enable by default only for inference (transcribe_speech, transcribe_speech_parallel).
One can still use CUDA graphs for validation in training by explicitly setting use_cuda_graph_decoder=True in decoding config.

Collection: [Note which collection this PR will affect]

Changelog

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

Usage

  • You can potentially add a usage example below
# Add a code snippet demonstrating how to use this 

GitHub Actions CI

The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.

The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".

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?

PR Type:

  • New Feature
  • Bugfix
  • Documentation

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

Who can review?

Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.

Additional Information

  • Related to # (issue)

* Enable CUDA graphs only for transcription. Sync streams before capture.

Signed-off-by: Vladimir Bataev <[email protected]>

* Apply isort and black reformatting

Signed-off-by: artbataev <[email protected]>

---------

Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: artbataev <[email protected]>
Co-authored-by: artbataev <[email protected]>
@artbataev artbataev merged commit acbd4e0 into main May 14, 2024
121 checks passed
@artbataev artbataev deleted the cherry-pick-main-bb26e9846f5e43b0381f1381a665cdcc73892eb3 branch May 14, 2024 17:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant