[TRITON] Select correct fp8_e4m3 type for gfx950#1433
Merged
lucas-santos-amd merged 2 commits intomainfrom Nov 28, 2025
Merged
Conversation
brunomazzottiamd
changed the title
fp8_e4m3 type for gfx950
brunomazzottiamd
changed the title
micmelesse
previously approved these changes
Nov 18, 2025
brunomazzottiamd
changed the title
fp8_e4m3 type for gfx950
brunomazzottiamd
force-pushed
the
bmazzott/fix_fav3_fp8_dtype
branch
2 times, most recently
from
3b303e1 to
ef1dacb
Compare
gyohuangxin
previously approved these changes
Nov 19, 2025
Member
gyohuangxin
left a comment
gyohuangxin
left a comment
There was a problem hiding this comment.
Thanks for improving the CI.
brunomazzottiamd
force-pushed
the
bmazzott/fix_fav3_fp8_dtype
branch
from
ef1dacb to
f10a0a4
Compare
micmelesse
previously approved these changes
Nov 19, 2025
brunomazzottiamd
dismissed stale reviews from micmelesse and gyohuangxin
via
cd90382
brunomazzottiamd
force-pushed
the
bmazzott/fix_fav3_fp8_dtype
branch
from
f10a0a4 to
cd90382
Compare
brunomazzottiamd
force-pushed
the
bmazzott/fix_fav3_fp8_dtype
branch
3 times, most recently
from
d5085d5 to
3002754
Compare
brunomazzottiamd
force-pushed
the
bmazzott/fix_fav3_fp8_dtype
branch
from
3002754 to
12093b9
Compare
Following GitHub Actions security recommendations available at <https://docs.github.com/en/actions/reference/security/ secure-use#use-an-intermediate-environment-variable>.
lucas-santos-amd
approved these changes
Nov 28, 2025
Contributor
Author
|
Michael Melesse approved the changes related to MHA Triton kernel and Xin Huang approved the changes related to CI. Their approvals were dismissed due to some rebases, but the diff content that was merged is the same. |
farlukas
pushed a commit
that referenced
this pull request
Dec 4, 2025
* Select correct `fp8_e4m3` type for `gfx950` * Avoid shell command substitution in PR title Following GitHub Actions security recommendations available at <https://docs.github.com/en/actions/reference/security/ secure-use#use-an-intermediate-environment-variable>.
nsusanto
pushed a commit
that referenced
this pull request
Dec 4, 2025
* Select correct `fp8_e4m3` type for `gfx950` * Avoid shell command substitution in PR title Following GitHub Actions security recommendations available at <https://docs.github.com/en/actions/reference/security/ secure-use#use-an-intermediate-environment-variable>.
zhuyuhua-v
pushed a commit
that referenced
this pull request
Dec 17, 2025
* Select correct `fp8_e4m3` type for `gfx950` * Avoid shell command substitution in PR title Following GitHub Actions security recommendations available at <https://docs.github.com/en/actions/reference/security/ secure-use#use-an-intermediate-environment-variable>.
valarLip
pushed a commit
that referenced
this pull request
Mar 18, 2026
* Select correct `fp8_e4m3` type for `gfx950` * Avoid shell command substitution in PR title Following GitHub Actions security recommendations available at <https://docs.github.com/en/actions/reference/security/ secure-use#use-an-intermediate-environment-variable>.
valarLip
pushed a commit
that referenced
this pull request
Mar 18, 2026
* Select correct `fp8_e4m3` type for `gfx950` * Avoid shell command substitution in PR title Following GitHub Actions security recommendations available at <https://docs.github.com/en/actions/reference/security/ secure-use#use-an-intermediate-environment-variable>.
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.
Motivation
FA v3 API introduced by #1065 sets the FP8 data type as
torch.float8_e4m3fnuz. However, this type isn't supported bygfx950and some unit tests were failing with errors raised by Triton compiler. We should usetorch.float8_e4m3fndata type forgfx950.I believe this detail went unnoticed in the original PR because our CI runs on
gfx942.Technical Details
Replace hardcoded
torch.float8_e4m3fnuzdata type by call toget_fp8_e4m3_dtype()AITER utility function. This function selects the FP8 data type supported by the architecture.Test Plan
Run
op_tests/triton_tests/test_mha.py, the test suite for Triton MHA.Test Result
Running
op_tests/triton_tests/test_mha.pyongfx950:mainbranch: 1344 failed, 6049 passed, 2112 skipped.test_mha_varlen[True-False-32-16-16-0.0-False-False-4-4-57]test_mha_varlen[True-False-32-16-16-0.0-False-False-4-4-128]Extra
This PR also fixes a CI security issue. It was possible to trigger remote code execution on CI hosts if PR title contained substrings enclosed between backticks, i.e.
`evil_command`.Submission Checklist