Significant performance improvement on MoE block of SwitchTransformer #30490
+51
−30
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Outdated suggestions cannot be applied.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?
This PR includes a performant implementation of
SwitchTransformersSparseMLP
in the Google SwitchTransformer.In the current implementation of the SwitchTransformer, it spans all possible experts, including the inactive ones.
This results in serious performance degradation of the SwitchTransformer.
As shown in this figure, the current implementation of the SwitchTransformer spans inactive experts, unnecessarily increasing latency. This issue can be particularly severe in models with a larger number of experts, as it needlessly spans more experts.However, in my custom implementation of
SwitchTransformersSparseMLP
, it only accesses and computes the active experts.Advantages
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.