Skip to content

Do not run benchmark for batch_size >= 16 on b580 #5423

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
merged 2 commits into from
Nov 4, 2025
Merged

Do not run benchmark for batch_size >= 16 on b580 #5423

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b264aad
Do not run benchmark for bach_size >= 16 on b580
etiotto Nov 3, 2025
8842125
Fix pre-commit
etiotto Nov 3, 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
6 changes: 6 additions & 0 deletions benchmarks/triton_kernels_benchmark/flex_attention_benchmark_causal_mask.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,12 @@ def causal_mask(_, __, q_idx, kv_idx):
batch_sizes = [16, 32, 64] if throughput_test else [batch_size]
fa_kernel_mode = os.getenv('FA_KERNEL_MODE', 'fwd')

if torch.xpu.get_device_name() == '580':
old_count = len(batch_sizes)
batch_sizes = [size for size in batch_sizes if size < 16]
if len(batch_sizes) != old_count:
print('Skipping running batch_sizes >= 16 on b580')


# Kernel profiling for Backward mode is not working as expected:
# For details: https://github.com/pytorch/pytorch/issues/144778
Expand Down
Loading