Skip to content

[Compiler Toolkit] Enable nested_compile_region on TransformerBlock #1973

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −0
Draft

[Compiler Toolkit] Enable nested_compile_region on TransformerBlock #1973

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 torchtitan/experiments/compiler_toolkit/llama3/parallelize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,10 @@ def validate_flex_attention_annotation(joint_with_descriptors):

def annotate_llama() -> None:
from torchtitan.models.attention import FlexAttentionWrapper
from torchtitan.models.llama3.model.model import TransformerBlock

# Mark TransformerBlock.forward as nested_compile_region
TransformerBlock.forward = torch.compiler.nested_compile_region(TransformerBlock.forward)

# annotate flex_attention with compile_with_inductor
FlexAttentionWrapper.forward = annotate_fn(
Expand Down
Loading