CUDA: Prefer vector flash decoding kernel for Gemma models #12738
Conversation
This file contains hidden or 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
Vector flash decoding kernel was not being picked for models with head dimension 256. Gemma models are in this category. Removing this limit improves e2e performance by upto 12% in gen phase throughput for Gemm models.
github-actions
bot
added
Nvidia GPU
JohannesGaessler
approved these changes
Apr 3, 2025
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
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Outdated suggestions cannot be applied.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.
Vector flash decoding kernel was not being picked for models with head dimension 256. Gemma models are in this category. Removing this limit improves e2e performance by up to 12% in gen phase throughput for Gemma models.
Performance:
RTX 4090, CUDA 12.8, Master vs PR