Skip to content
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

Jump to bottom

[Quant] Use finite hops to check if the quant nodes are connected with producer #108572

Closed
wants to merge 5 commits into from
Closed

[Quant] Use finite hops to check if the quant nodes are connected with producer #108572

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a157a8f
[Quant] Move to BFS instead of DFS to check for connectedness
kimishpatel Sep 5, 2023
4afca26
Update on "[Quant] Move to BFS instead of DFS to check for connectedn…
kimishpatel Sep 5, 2023
3daeb0b
Update on "[Quant] Move to BFS instead of DFS to check for connectedn…
kimishpatel Sep 5, 2023
65af5ed
Update on "[Quant] Move to BFS instead of DFS to check for connectedn…
kimishpatel Sep 6, 2023
369b403
Update on "[Quant] Move to BFS instead of DFS to check for connectedn…
kimishpatel Sep 6, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
16 changes: 11 additions & 5 deletions torch/ao/quantization/pt2e/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@

from torch.ao.quantization.quantizer import QuantizationAnnotation

import queue

__all__ = [
"fold_bn_weights_into_conv_node",
"get_aten_graph_module",
Expand All @@ -35,13 +37,17 @@


def _is_connected(next_node: torch.fx.Node, target: torch.fx.Node) -> bool:
if target.op == "output":
return False
if next_node == target:
return True
q = queue.Queue()

Check failure on line 40 in torch/ao/quantization/pt2e/utils.py

View workflow job for this annotation

GitHub Actions / lintrunner / linux-job

MYPY [var-annotated] 

Need type annotation for "q"
for n in next_node.users.keys():
if _is_connected(n, target):
q.put(n)
while not q.empty():
node = q.get()
if node.op == "output":
return False
if node == target:
return True
for n in node.users.keys():
q.put(n)
return False


Expand Down