fix map_to_kv_tensors/unmap_from_kv_tensors in MLA non-contiguous layout#357
Open
lianghao208 wants to merge 1 commit into
Open
fix map_to_kv_tensors/unmap_from_kv_tensors in MLA non-contiguous layout#357lianghao208 wants to merge 1 commit into
lianghao208 wants to merge 1 commit into
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In MLA models with a non-contiguous layout,
map_to_kv_tensorsandunmap_from_kv_tensorsperform redundant mapping for both K and V individually. Under the MLA architecture, this double-mapping approach results in a 50% waste of memory.