Multi step scheduling #441
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
… Trzeba dojść dlaczego
Currently before each Sampler call we have a CPU sync, which causes a host gap: <img width="226" alt="image" src="https://github.com/user-attachments/assets/4509e69b-0f16-4ac9-812e-a2a9bc43a6ad"> This PR is removing that sync, so the host gap is no longer visible: <img width="133" alt="image" src="https://github.com/user-attachments/assets/66c19e4b-d832-4955-848d-8ae4acd8d264"> NOTE: class `ApplyToppTopkScalar` still has some CPU syncs inside. It means that the biggest gain will be observed in the scenario without `top_p` or `top_k` parameters. I think it is worth to investigate if we can remove the syncs from this function too.
… Trzeba dojść dlaczego
tzielinski-habana
requested review from
kdamaszk,
kzawora-intel,
jmaksymczuk,
madamczykhabana,
adobrzyniewicz-habana,
afierka-intel,
iboiko-habana and
michalkuligowski
kdamaszk
approved these changes
Oct 29, 2024
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Outdated suggestions cannot be applied.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.
Implementation of multi-step scheduling. To use the feature, pass --num_scheduler_steps=[n] as a server parameter. In my tests, best results were achieved with n==64, but this will vary depending on the model.