Skip to content

[WIP][FA][Blackwell] Implementation with explicit data partitioning #384

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
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[WIP][FA][Blackwell] Implementation with explicit data partitioning #384

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4f313c3
add explicit data partition variant
manman-ren Aug 31, 2025
a24fa6a
tuning
manman-ren Sep 2, 2025
82c5e65
persistent
manman-ren Sep 10, 2025
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
10 changes: 5 additions & 5 deletions tritonbench/kernels/blackwell_triton_fused_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,9 +141,9 @@ def _host_descriptor_pre_hook(nargs):
if is_hip():
NUM_STAGES_OPTIONS = [1]
elif supports_host_descriptor():
NUM_STAGES_OPTIONS = [2, 3, 4]
NUM_STAGES_OPTIONS = [3]
else:
NUM_STAGES_OPTIONS = [2, 3, 4]
NUM_STAGES_OPTIONS = [3]

configs = [
triton.Config(
Expand All @@ -152,10 +152,10 @@ def _host_descriptor_pre_hook(nargs):
num_warps=w,
pre_hook=_host_descriptor_pre_hook,
)
for BM in [64, 128]
for BN in [32, 64, 128]
for BM in [128]
for BN in [128]
for s in NUM_STAGES_OPTIONS
for w in [4, 8]
for w in [4]
]


Expand Down
Loading
Loading