Skip to content

Return the exported_program from transform to allow internal usage #6210

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

Closed
wants to merge 1 commit into from
Closed

Return the exported_program from transform to allow internal usage #6210

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: 4 additions & 4 deletions backends/qualcomm/utils/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
import operator
import warnings
from collections import OrderedDict
from typing import Callable, Dict, List, Set, Tuple
from typing import Callable, Dict, FrozenSet, List, Set, Tuple

import executorch.backends.qualcomm.python.PyQnnManagerAdaptor as PyQnnManagerAdaptor

Expand Down Expand Up @@ -290,9 +290,8 @@ def get_decomp_table() -> Dict[torch._ops.OperatorBase, Callable]:


def _transform(
edge_program: ExportedProgram, custom_pass_config: Set[str] = None
) -> None:
custom_pass_config = custom_pass_config or {}
edge_program: ExportedProgram, custom_pass_config: FrozenSet[str] = frozenset()
) -> ExportedProgram:
# currently ExirExportedProgram.transform does not accept
# changes of input number which was caused by FoldQDQ
# apply passes one by one here to avoid IR capture failure
Expand Down Expand Up @@ -322,6 +321,7 @@ def _transform(
edge_program.graph_module,
)
edge_program._validate()
return edge_program


def capture_program(
Expand Down
Loading