[ROCm][Bugfix] Aiter mha fp8 fix #24991
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
dllehr-amd
requested review from
DarkLight1337,
LucasWilkinson,
NickLucche,
ProExpertProg,
WoosukKwon,
aarnphm,
alexm-redhat,
comaniac,
gshtras,
hmellor,
houseroad,
mgoin,
njhill,
robertgshaw2-redhat,
simon-mo,
tdoublep,
tlrmchlsmth,
yewentao256,
youkaichao,
ywang96 and
zou3519
as code owners
mergify
bot
added
documentation
gshtras
removed request for
DarkLight1337,
WoosukKwon,
alexm-redhat,
gshtras,
houseroad,
robertgshaw2-redhat,
yewentao256 and
ywang96
dllehr-amd
force-pushed
the
aiter_mha_fp8_fix
branch
from
e69addc to
d12d4ea
Compare
gshtras
added a commit
to ROCm/vllm
that referenced
this pull request
Sep 17, 2025
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Change f8 kv-cache check in rocm_aiter_fa.py to account for both float8_e4m3fnuz and float8_e4m3fn datatypes. Signed-off-by: Doug Lehr <douglehr@amd.com>
dllehr-amd
force-pushed
the
aiter_mha_fp8_fix
branch
from
d12d4ea to
d662144
Compare
gshtras
approved these changes
Sep 17, 2025
github-project-automation
bot
moved this from To Triage
to Ready
in gpt-oss Issues & Enhancements
github-project-automation
bot
moved this from Ready
to Done
in gpt-oss Issues & Enhancements
debroy-rh
pushed a commit
to debroy-rh/vllm
that referenced
this pull request
Sep 19, 2025
Signed-off-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com>
FeiDaLI
pushed a commit
to FeiDaLI/vllm
that referenced
this pull request
Sep 25, 2025
Signed-off-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com>
charlifu
pushed a commit
to ROCm/vllm
that referenced
this pull request
Sep 25, 2025
Signed-off-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com> Signed-off-by: charlifu <charlifu@amd.com>
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 10, 2025
Signed-off-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com> Signed-off-by: xuebwang-amd <xuebwang@amd.com>
choprahetarth
pushed a commit
to Tandemn-Labs/vllm
that referenced
this pull request
Oct 11, 2025
Signed-off-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com>
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 24, 2025
Signed-off-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com> Signed-off-by: xuebwang-amd <xuebwang@amd.com>
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.
Fixes accuracy when using VLLM_ROCM_USE_AITER_MHA=1 on gfx architectures that use torch.float8_e4m3fn datatypes
Purpose
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.