Flat KV cache layout#152
Merged
Merged
Conversation
kdamaszk
force-pushed
the
dev/kdamaszke/flat_kv_cache
branch
from
8084403 to
9238f7a
Compare
kdamaszk
requested review from
afierka-intel,
kzawora-intel,
mgawarkiewicz,
michalkuligowski and
tzielinski-habana
as code owners
michalkuligowski
approved these changes
Apr 17, 2025
kdamaszk
requested review from
jikunshang,
madamczyk-intel,
mgawarkiewicz-intel and
xuechendi
as code owners
kdamaszk
force-pushed
the
dev/kdamaszke/flat_kv_cache
branch
from
6244ad1 to
6a1204c
Compare
madamczyk-intel
previously requested changes
May 8, 2025
kdamaszk
force-pushed
the
dev/kdamaszke/flat_kv_cache
branch
from
16e4622 to
e14cc97
Compare
kdamaszk
force-pushed
the
dev/kdamaszke/flat_kv_cache
branch
from
277f5fe to
6ebec4b
Compare
kzawora-intel
approved these changes
May 20, 2025
kzawora-intel
approved these changes
May 20, 2025
kwisniewski98
pushed a commit
that referenced
this pull request
Jun 2, 2025
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
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Change the layout of KV cache to (num_blocks * block_size, num_kv_heads, head_size). This will improve the performance as update will be done on 1D indices which will remove unnecessary transpose and memcopies due to low FCD.
Corresponding change: HabanaAI/vllm-fork#1106