Skip to content

⚡️ Speed up function is_layer_skipped_quant by 15% #332

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 1 commit into
base: main
Choose a base branch
from
Open

⚡️ Speed up function is_layer_skipped_quant by 15% #332

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
8 changes: 7 additions & 1 deletion python/sglang/srt/layers/quantization/moe_wna16.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,13 @@ def get_quant_method(


def is_layer_skipped_quant(prefix: str, modules_to_not_convert: List[str]):
return any(module_name in prefix for module_name in modules_to_not_convert)
# Optimize by short-circuiting for empty list, and avoid generator overhead by using set lookup if possible.
# However, the logic is substring matching not equality, so fastest is to avoid any function call per loop.
# Hoisting 'in' out of generator expression for micro-optimization, and eliminate generator object.
for module_name in modules_to_not_convert:
if module_name in prefix:
return True
return False


class MoeWNA16Method(FusedMoEMethodBase):
Expand Down