Skip to content

fix deepgemm_fp8_paged_mqa_logits kernel input parameter mismatch issue #3604

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

Open
lirui927 wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −0
Open

fix deepgemm_fp8_paged_mqa_logits kernel input parameter mismatch issue #3604

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions aiter/ops/triton/attention/pa_mqa_logits.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -506,6 +506,7 @@ def deepgemm_fp8_paged_mqa_logits(
)
if triton_version >= Version("3.5.0"):
cdna_version = get_cdna_version()
is_gfx1250 = get_gfx() == "gfx1250"
kernel[grid](
batch_size,
next_n,
Expand Down Expand Up @@ -533,6 +534,7 @@ def deepgemm_fp8_paged_mqa_logits(
KVBlockSize,
hidden_dim,
cdna_version,
is_gfx1250,
)
else: # load AOT compiled gluon kernel
assert triton_version < Version(
Expand Down
Loading