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

Lower memory usage for ICL #2691

Closed
wants to merge 5 commits into from
Closed

Conversation

dakinggg
Copy link
Contributor

@dakinggg dakinggg commented Nov 6, 2023

What does this PR do?

What issue(s) does this change relate to?

Before submitting

  • Have you read the contributor guidelines?
  • Is this change a documentation change or typo fix? If so, skip the rest of this checklist.
  • Was this change discussed/approved in a GitHub issue first? It is much more likely to be merged if so.
  • Did you update any related docs and document your change?
  • Did you update any related tests and add any new tests related to your change? (see testing)
  • Did you run the tests locally to make sure they pass?
  • Did you run pre-commit on your change? (see the pre-commit section of prerequisites)

@bmosaicml
Copy link
Contributor

Do you have any idea how this is affecting the overall run time? Writing to/from a cache file may be slow.

One alternative design I was considering would be writing the encoded_dataset to instead be a generator pointing to a prep_example function that uses a yield statement to lazily execute. Not sure if this would work with the rest of composer though since it seems datasets require support of indexing?

@dakinggg
Copy link
Contributor Author

Closing in favor of #2713

1 similar comment
@dakinggg
Copy link
Contributor Author

Closing in favor of #2713

@dakinggg dakinggg closed this Nov 30, 2023
@dakinggg dakinggg deleted the low-mem-icl branch February 10, 2024 07:29
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