[CK_TILE] Tune fmha fwd splitkv codgen #1717
Draft
+359
−255
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
Contributor
poyenc
commented
Dec 4, 2024
•
poyenc
commented
- Add instances to enable vector load on hdim_q/hdim_v
- Use larger tile size (kM0) for chunked prefill (group + paged-kvcache)
- Update num_splits heuristic (determine # workgroup base on the prefill/decode phase)
poyenc
requested review from
junliume,
illsilin,
carlushuang,
qianfengz,
aosewski,
geyyer,
bartekxk and
andriy-ca
as code owners
|
I've encountered some flash-attention test failure. I'm investigating the root cause. |
poyenc
force-pushed
the
feature/add-splitkv-instance
branch
from
be51207 to
488bfab
Compare
|
I cannot figure out why the FA tests fail after I added those new instances. Close this PR for now. |
poyenc
force-pushed
the
feature/add-splitkv-instance
branch
from
8429854 to
ed634ea
Compare
…ature/add-splitkv-instance
…ature/add-splitkv-instance
poyenc
changed the title
|
the FA test failure had been fixed |
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Outdated suggestions cannot be applied.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.