[AutoDeploy]: switch [1,sl] layout instead of [b,sl] for model export
Open
Nobody has claimed this yet.
AutoDeploy
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
🚀 The feature, motivation and pitch
Right now we export with layout [b,s] in the inputs and later switch to [1, s]. This has two issues:
- Handle the overhead of converting between the two formats
- Doesn't allow for model onboarding that might hard-code their implementation to
b=1(e.g. the HF step3 checkpoint) or that already handle some type of "flattened sequences".
Alternatives
No response
Additional context
No response
Before submitting a new issue...
- Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.