Skip to content

Conversation

@jeffra
Copy link
Contributor

@jeffra jeffra commented Nov 1, 2022

  • SD benchmark scripts
  • SD tutorial showing how to deploy and evaluate a deployment
  • Add MII package version that can be checked at runtime
  • Fix GPRC max message size issue that I ran into when running multi-batch SD
  • Added optional mii config to skip model validation checks (this currently takes >15sec and is not always needed)

Copy link
Contributor

@mrwyattii mrwyattii left a comment

Choose a reason for hiding this comment

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

LGTM, just a few minor suggestions to tutorial

samyam and others added 5 commits November 3, 2022 12:43
A bit of restructuring
Co-authored-by: Michael Wyatt <michaelwyatt@microsoft.com>
Co-authored-by: Michael Wyatt <michaelwyatt@microsoft.com>
@Suhail
Copy link

Suhail commented Nov 8, 2022

I'd recommend you mention how many steps are taken for the benchmark comparison. Same with image dimensions. Both really impact throughput. Maybe try compare variations like 512x512 vs 1024x1024.

I didn't immediately find it so apologies if I missed it too.

@jeffra
Copy link
Contributor Author

jeffra commented Nov 8, 2022

Thank you @Suhail for the feedback, I’ll update the tutorial before merging to add this info.

One thing for anyone reading this PR, we have pending changes coming later today on the DeepSpeed side related further performance updates and bug fixes. We’ll merge this PR once those our live.

@jeffra jeffra merged commit 79b56af into main Nov 9, 2022
@jeffra jeffra deleted the sd-bench branch November 9, 2022 20:12
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.

7 participants