[KVCache] TIR attention kernel support for MLA #17618
Merged
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
MasterJH5574
force-pushed
the
tvm-dev/2025-02-01-tir-mla
branch
7 times, most recently
from
98f36e1 to
0ab745e
Compare
Contributor
Author
|
@tvm-bot rerun |
This PR introduces the MLA attention kernels written in TIR. It also implements the KV cache MLA computation logic. A new unit test file is added to ensure the correctness of the TIR kernels. This PR also fixes a few TIR prefill kernel tile size initialization.
MasterJH5574
force-pushed
the
tvm-dev/2025-02-01-tir-mla
branch
from
0ab745e to
dfa4d07
Compare
jinhongyii
approved these changes
Feb 5, 2025
ShiboXing
pushed a commit
to ShiboXing/tvm
that referenced
this pull request
Aug 10, 2025
This PR introduces the MLA attention kernels written in TIR. It also implements the KV cache MLA computation logic. A new unit test file is added to ensure the correctness of the TIR kernels. This PR also fixes a few TIR prefill kernel tile size initialization.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
This PR introduces the MLA attention kernels written in TIR. It also implements the KV cache MLA computation logic.
A new unit test file is added to ensure the correctness of the TIR kernels.
This PR also fixes a few TIR prefill kernel tile size initialization.