You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The implementation of tree attention which will been used for accelerating the speculative decodign and parallel decoding (with sampling params: n lager than 1 and beam_search = false. Theoretically, the case where beam_search=True can also be implemented, but it has not been implemented yet in this PR.）
@yukavio great work, will you continue work on this PR.
There are certain performance issues with the kernel implemented using Triton. If a high acceleration ratio is required, it may be necessary to modify the implementation based on CUDA. However, I'm sorry to say that I currently don't have the time to complete this task.
This pull request has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this pull request should remain open. Thank you!
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The implementation of tree attention which will been used for accelerating the speculative decodign and parallel decoding (with sampling params:
nlager than 1 and beam_search = false. Theoretically, the case where beam_search=True can also be implemented, but it has not been implemented yet in this PR.）