Add feature to initialize hidden state in Selective Scan #806
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
…inimising memory and time overhead and without modifying the cuda kernel
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This pull request adds a new function to the
mamba_ssm/ops/selective_scan_interface.pyfile that enables initialization of the hidden state for the selective scan operation. This enhancement allows users to specify an initial hidden state, improving flexibility and potential use cases for the selective scan kernel.New functionality for hidden state initialization:
select_scan_fn_init_hiddenfunction, which allows users to initialize the hidden state in the selective scan operation by transformingBand applying a kernel method with minimal memory and time overhead.