feat: non-contiguous query with paged kv cache #553
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
Signed-off-by: LinHeLurking <[email protected]>
reyoung
reviewed
Oct 24, 2024
reyoung
reviewed
Oct 24, 2024
reyoung
reviewed
Oct 24, 2024
reyoung
reviewed
Oct 24, 2024
reyoung
reviewed
Oct 24, 2024
reyoung
reviewed
Oct 24, 2024
Signed-off-by: LinHeLurking <[email protected]>
yzh119
approved these changes
Oct 25, 2024
There was a problem hiding this comment.
Thanks for your contribution @LinHeLurking and thank @reyoung for the review!
tsu-bin
added a commit
to tsu-bin/flashinfer_dev
that referenced
this pull request
Oct 30, 2024
tsu-bin
added a commit
to tsu-bin/flashinfer_dev
that referenced
this pull request
Oct 30, 2024
yzh119
pushed a commit
that referenced
this pull request
Oct 30, 2024
Hi, when I try to rebase my current work, just found cpp integration (benchmark and test) failed to build, this is introduced by the feature #553. Tests have been passed. Co-authored-by: tsu-bin <[email protected]>
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Outdated suggestions cannot be applied.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.
Motivation
Previously, only ragged version of prefill kernel supported non-contiguous query tensor (#404). But with paged kv cache, you have to make query tensor contiguous. Libraries like vLLM or SGLang must make query tensor contiguous before calling flashinfer kernels (vLLM call of flashinfer, SGLang call of flashinfer). This PR solves it, ensuring that prefill/decode kernels with paged kv cache support non-contiguous query tensor.
Main Changes
BatchPrefillPagedParamsandBatchDecodeParams.The Python interfaces remain the same. Nothing changes except it accepts non-contiguous query tensors now!