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.

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

Improvements in AOT UX #787

Merged
merged 7 commits into from
Jun 8, 2023
Merged

Improvements in AOT UX #787

merged 7 commits into from
Jun 8, 2023

Conversation

sindhuvahinis
Copy link
Contributor

@sindhuvahinis sindhuvahinis commented May 31, 2023 •
edited
Loading

UX improvement

  • Making serving.properties optional from UX (giving serving.properties should also work), Add —engine (optional), —tensor-parallel-degree, —save-mp-checkpoint-path as command line arguments
  • Add option.parallel_loading=true in generated serving.properties
  • Remove option.model_dir in generated serving.properties in DeepSpeed
  • Load back the checkpoints for DS and if Ds does not support checkpoint loading, fail the partition.

Tests were successful:
https://github.com/deepjavalibrary/djl-serving/actions/runs/5184767762

@sindhuvahinis sindhuvahinis requested review from zachgk, frankfliu and a team as code owners May 31, 2023 23:57
@sindhuvahinis sindhuvahinis marked this pull request as draft June 1, 2023 00:52
@sindhuvahinis sindhuvahinis marked this pull request as ready for review June 5, 2023 16:34
@sindhuvahinis sindhuvahinis force-pushed the improve_aot branch 2 times, most recently from 4898ab6 to 1dcd086 Compare June 6, 2023 02:46
@sindhuvahinis sindhuvahinis merged commit c3ea2e4 into master Jun 8, 2023
@sindhuvahinis sindhuvahinis deleted the improve_aot branch June 8, 2023 17:01
@sindhuvahinis sindhuvahinis mentioned this pull request Jun 12, 2023
Closed
KexinFeng pushed a commit to KexinFeng/djl-serving-forked that referenced this pull request Aug 16, 2023
@sindhuvahinis @frankfliu
Improvements in AOT UX (deepjavalibrary#787)
2009312 
* Improvements in AOT UX

* [partition] Override options with command line arguments

---------

Co-authored-by: Frank Liu <frankfliu2000@gmail.com>
KexinFeng pushed a commit to KexinFeng/djl-serving-forked that referenced this pull request Aug 16, 2023
@sindhuvahinis @frankfliu @KexinFeng
Improvements in AOT UX (deepjavalibrary#787)
86e82cf 
* Improvements in AOT UX

* [partition] Override options with command line arguments

---------

Co-authored-by: Frank Liu <frankfliu2000@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@frankfliu frankfliu frankfliu approved these changes

@lanking520 lanking520 lanking520 left review comments

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

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@sindhuvahinis @lanking520 @frankfliu