Skip to content

Fp8 block scale quantization for fmha fwd #3330

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
illsilin merged 34 commits into from
Jan 22, 2026
Merged

Fp8 block scale quantization for fmha fwd #3330

illsilin merged 34 commits into from
Jan 22, 2026

Conversation

@ltqin
Copy link
Collaborator

@ltqin ltqin commented Dec 1, 2025

Proposed changes

Implement fp8 block scale quantization for fmha fwd

Checklist

./build/bin/tile_example_fmha_fwd -init=3 -b=16 -s=256 -s_k=1024 -h=16 -h_k=1 -d=128 -prec=fp8bf16 -vlayout=r -qscale=2 -kname=1 -mode=0 -v=1 -operm=1 -iperm=1

@ltqin ltqin requested a review from rocking5566 December 3, 2025 00:26
poyenc
poyenc reviewed Jan 16, 2026
View reviewed changes
@poyenc
Copy link
Contributor

poyenc commented Jan 19, 2026

LGTM. Please make this PR won't introduce performance regression before mergin it.

poyenc
poyenc previously approved these changes Jan 19, 2026
View reviewed changes
@ltqin ltqin enabled auto-merge (squash) January 20, 2026 06:21
@ltqin ltqin disabled auto-merge January 20, 2026 06:22
@ltqin ltqin enabled auto-merge (squash) January 20, 2026 14:09
@ltqin ltqin disabled auto-merge January 20, 2026 14:09
@illsilin
Copy link
Collaborator

illsilin commented Jan 20, 2026

Please let's make sure we don't break AITER with these changes!

@poyenc
Copy link
Contributor

poyenc commented Jan 21, 2026

@ltqin could you update the CHANGELOG.md as well?

@ltqin ltqin requested review from a team and ddembeckAMD as code owners January 21, 2026 04:09
@ltqin ltqin enabled auto-merge (squash) January 22, 2026 03:48
@ltqin ltqin disabled auto-merge January 22, 2026 03:49
@illsilin illsilin merged commit dd0b429 into develop Jan 22, 2026
12 checks passed
@illsilin illsilin deleted the ck_tile/fmha_fwd_block_scale branch January 22, 2026 04:58
poyenc added a commit that referenced this pull request Jan 23, 2026
@poyenc
Revert " Fp8 block scale quantization for fmha fwd (#3330)"
ade7cda 
This reverts commit dd0b429.
@poyenc poyenc mentioned this pull request Jan 23, 2026
Merged
illsilin pushed a commit that referenced this pull request Jan 23, 2026
@poyenc
Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#3633)
de5a1d7 
This reverts commit dd0b429.
ltqin added a commit that referenced this pull request Jan 23, 2026
@ltqin
Revert "Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#…
5ae8f27 
…3633)"

This reverts commit de5a1d7.
illsilin added a commit that referenced this pull request Jan 23, 2026
@ltqin @illsilin
Revert "Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#…
67f0b74 
…3633)" (#3635)

This reverts commit de5a1d7.

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@rocking5566 rocking5566 rocking5566 left review comments

Copilot code review Copilot Copilot left review comments

@poyenc poyenc poyenc approved these changes

@illsilin illsilin Awaiting requested review from illsilin illsilin is a code owner

@carlushuang carlushuang Awaiting requested review from carlushuang carlushuang is a code owner

@qianfengz qianfengz Awaiting requested review from qianfengz qianfengz is a code owner

@aosewski aosewski Awaiting requested review from aosewski aosewski is a code owner

@geyyer geyyer Awaiting requested review from geyyer geyyer is a code owner

@bartekxk bartekxk Awaiting requested review from bartekxk bartekxk is a code owner

@andriy-ca andriy-ca Awaiting requested review from andriy-ca andriy-ca is a code owner

@afagaj afagaj Awaiting requested review from afagaj afagaj is a code owner

@asleepzzz asleepzzz Awaiting requested review from asleepzzz asleepzzz is a code owner

@tenpercent tenpercent Awaiting requested review from tenpercent tenpercent is a code owner

@ThomasNing ThomasNing Awaiting requested review from ThomasNing ThomasNing is a code owner

@coderfeli coderfeli Awaiting requested review from coderfeli coderfeli is a code owner

@cgmillette cgmillette Awaiting requested review from cgmillette cgmillette is a code owner

@shumway shumway Awaiting requested review from shumway shumway is a code owner

@vidyasagar-amd vidyasagar-amd Awaiting requested review from vidyasagar-amd vidyasagar-amd is a code owner

@vpietila-amd vpietila-amd Awaiting requested review from vpietila-amd vpietila-amd is a code owner

@Snektron Snektron Awaiting requested review from Snektron Snektron is a code owner

@ddembeckAMD ddembeckAMD Awaiting requested review from ddembeckAMD ddembeckAMD is a code owner

Assignees

@asleepzzz asleepzzz

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@ltqin @poyenc @illsilin @rocking5566 @asleepzzz