Skip to content

Log when thd with dropout falls to the composite cuDNN engine #3313

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
bzantium wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −0
Open

Log when thd with dropout falls to the composite cuDNN engine #3313

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
7 changes: 7 additions & 0 deletions transformer_engine/pytorch/attention/dot_product_attention/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1082,6 +1082,13 @@ def _is_fa3_supported(num_heads, num_gqa_groups, head_dim_qk, head_dim_v, qkv_dt
if use_flash_attention_4 and FlashAttentionUtils.v4_is_installed:
logger.debug("Disabling FlashAttention 4 for dropout")
use_flash_attention_4 = False
if use_fused_attention and qkv_format == "thd":
# Dropout keeps thd off cuDNN's unified engine, so it falls to the much slower
# composite one. Nothing else reports this.
logger.debug(
"FusedAttention with dropout and qkv_format = thd uses the composite cuDNN"
" engine, which is much slower than the unified engine"
)
Comment on lines +1085 to +1091

@greptile-apps greptile-apps Bot Aug 4, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Advisory precedes backend selection

The advisory runs before later filters can reject FusedAttention, so configurations such as thd with dropout and an arbitrary mask log that the composite cuDNN engine is in use even though another backend is ultimately selected. This sends users toward the wrong performance diagnosis; emit the advisory only after final FusedAttention selection.

Knowledge Base Used: PyTorch Attention Stack

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!


# Filter: Softmax type
# context_parallel | softmax_type | supported backends
Expand Down