Skip to content

Use Triton GroupNorm on H100 #106

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

Merged
PatrickRMiles merged 1 commit into from
Sep 22, 2026
Merged

Use Triton GroupNorm on H100 #106

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
4 changes: 4 additions & 0 deletions scripts/scaffold-matrix.job
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,10 @@

export LD_LIBRARY_PATH=/usr/lib64:$LD_LIBRARY_PATH

# Use Triton compiled channels-last groupnorm instead of PyTorch compiled contiguous groupnorm, which will incur an extra channels-last conversion.
# The Triton GN is optimized for AMD MI300A, but we have still noticed almost ~2x improved performance on H100.
export SCAFFOLD_GROUPNORM_TRITON=1

CONFIG_PATH="$(pwd)/ScaFFold/configs/benchmark_default.yml"

scaffold generate_fractals \
Expand Down
Loading