Change Phi3 _supports_sdpa to True
#32457
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ArthurZucker
approved these changes
Aug 6, 2024
|
@ArthurZucker I think it is all green now~! |
|
Thanks! |
3 tasks
yundai424
pushed a commit
to linkedin/Liger-Kernel
that referenced
this pull request
Aug 27, 2024
## Summary Add a new monkeypatch function to support patching Huggingface's Phi3 implementation with Liger Kernels. Phi3 has its own MLP implementation (`Phi3MLP`) so a `LigerPhi3SwiGLUMLP` implementation that leverages `LigerSiLUMulFunction` is provided as well. ## Testing Done - [x] run `make test` to ensure correctness - [x] run `make checkstyle` to ensure code style - [x] run `make test-convergence` to ensure convergence Convergence test added (and passing on my 4090) for a minimodel based on Phi3 patched with liger kernels. All tests passing. ## Questions for Discussion Apparently Phi3 was only added in [transformers v4.41](https://github.com/huggingface/transformers/releases/tag/v4.41.0), but the lowest supported version of transformers in Liger-Kernel is 4.40.1. Additionally, only more recently has [`sdpa` been supported in HF Phi3](huggingface/transformers#32457). Thoughts? Should I leave the transformers dependency version as-is?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Change Phi3 model's sdpa support from False to True.
Fixes #31863
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@ArthurZucker