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

[Wanda Refactor] TerminalModuleCompressor contract #1885

Closed
wants to merge 7 commits into from

Conversation

rahul-tuli
Copy link
Member

@rahul-tuli rahul-tuli commented Dec 7, 2023

This PR removes some code duplicacy b/w SparseGPT and WandaGPT by defining a contract and Moving common functionality to a base class

Subsequent diffs will do similar refactor for LayerCompressor and the actual WandaModifier

@rahul-tuli rahul-tuli changed the base branch from main to wanda December 7, 2023 14:54
@rahul-tuli rahul-tuli marked this pull request as ready for review December 7, 2023 14:59
@rahul-tuli rahul-tuli self-assigned this Dec 7, 2023
Copy link
Contributor

@Satrat Satrat left a comment

Choose a reason for hiding this comment

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

LGTM, I like the inclusion of the contract class. My one nit is I'd prefer all the "GPT" classes live in different files, one base, sparseGPT and Wanda.

src/sparseml/modifiers/utils/gpt_helpers.py Outdated Show resolved Hide resolved
src/sparseml/modifiers/utils/gpt_helpers.py Outdated Show resolved Hide resolved
src/sparseml/modifiers/utils/gpt_helpers.py Outdated Show resolved Hide resolved
@rahul-tuli rahul-tuli mentioned this pull request Dec 7, 2023
3 tasks
@rahul-tuli
Copy link
Member Author

LGTM, I like the inclusion of the contract class. My one nit is I'd prefer all the "GPT" classes live in different files, one base, sparseGPT and Wanda.

Done!

Copy link
Member

@bfineran bfineran left a comment

Choose a reason for hiding this comment

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

LGTM pending comment and naming as discussed

torch.backends.cudnn.allow_tf32 = False


class TerminalModuleCompressor(ABC):
Copy link
Member

Choose a reason for hiding this comment

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

would be good to get rid of this since we just have 1 implementor class and don't expect any in the near future

@rahul-tuli rahul-tuli changed the title [Wanda Refactor] GPT contract [Wanda Refactor] TerminalModuleCompressor contract Dec 12, 2023
rahul-tuli added a commit that referenced this pull request Dec 18, 2023
@rahul-tuli
Copy link
Member Author

Closingg cause requested updates are now a part of #1887

@rahul-tuli rahul-tuli closed this Dec 18, 2023
rahul-tuli added a commit that referenced this pull request Dec 18, 2023
* Define GPT contract

* rename tmp -> batch_size

* Define LayerCompressor Contract

* Rename gpt_helpers to gpts
Fix some docstrings

* add named argument to function call

* Wanda/OBCQ refactor

* propagate target-ids

* Address review comments from
* #1885
* #1886
@rahul-tuli rahul-tuli deleted the define-gpt-contract branch December 19, 2023 21:11
rahul-tuli added a commit that referenced this pull request Dec 28, 2023
* Add wanda base

* Initial implementation

* Update Wanda Base

* Refactor to use WandaLayerCompressor
Update WrappedGPT

* Rename WrappedGPT to WandaGPT

* [Wanda Refactor] Wanda/OBCQ Modifier Refactor (#1887)

* Define GPT contract

* rename tmp -> batch_size

* Define LayerCompressor Contract

* Rename gpt_helpers to gpts
Fix some docstrings

* add named argument to function call

* Wanda/OBCQ refactor

* propagate target-ids

* Address review comments from
* #1885
* #1886

* Fix typo

* Update test

* Fix regression
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.

None yet

3 participants