Skip to content

Qualcomm AI Engine Direct - Deprecate convert_bmm_to_matmul pass #11392

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 3 commits into
base: main
Choose a base branch
from
Open

Qualcomm AI Engine Direct - Deprecate convert_bmm_to_matmul pass #11392

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
858fd02
Qualcomm AI Engine Direct - Deprecate convert_bmm_to_matmul pass
DannyYuyang-quic Jun 5, 2025
35061b8
Merge branch 'main' into dev1/danny/deprecate_convert_bmm_to_matmul_pass
DannyYuyang-quic Jun 6, 2025
c43e821
Merge branch 'main' into dev1/danny/deprecate_convert_bmm_to_matmul_pass
DannyYuyang-quic Jun 6, 2025
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
2 changes: 0 additions & 2 deletions backends/qualcomm/_passes/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@
from .annotate_quant_attrs import AnnotateQuantAttrs
from .annotate_stack import AnnotateStack
from .annotate_unbind import AnnotateUnbind
from .convert_bmm_to_matmul import ConvertBmmToMatmul
from .convert_conv1d_to_conv2d import ConvertConv1dToConv2d
from .convert_square_to_pow import ConvertSquareToPow
from .decompose_any import DecomposeAny
Expand Down Expand Up @@ -45,7 +44,6 @@
AnnotateQuantAttrs,
AnnotateStack,
AnnotateUnbind,
ConvertBmmToMatmul,
ConvertConv1dToConv2d,
ConvertSquareToPow,
DecomposeAny,
Expand Down
76 changes: 0 additions & 76 deletions backends/qualcomm/_passes/convert_bmm_to_matmul.py
View file
Open in desktop

This file was deleted.

2 changes: 0 additions & 2 deletions backends/qualcomm/_passes/qnn_pass_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,6 @@
AnnotateQuantAttrs,
AnnotateStack,
AnnotateUnbind,
ConvertBmmToMatmul,
ConvertConv1dToConv2d,
ConvertSquareToPow,
DecomposeAny,
Expand Down Expand Up @@ -80,7 +79,6 @@ def get_capture_program_passes():
(AnnotateQuantAttrs, True),
(AnnotateStack, True),
(AnnotateUnbind, True),
(ConvertBmmToMatmul, True),
(ConvertConv1dToConv2d, True),
(DecomposeAny, True),
(DecomposeColIm, True),
Expand Down
3 changes: 0 additions & 3 deletions backends/qualcomm/_passes/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,6 @@ def get_passes_dependency_for_capture_program():
AnnotateQuantAttrs,
AnnotateStack,
AnnotateUnbind,
ConvertBmmToMatmul,
ConvertConv1dToConv2d,
DecomposeAny,
DecomposeColIm,
Expand All @@ -85,12 +84,10 @@ def get_passes_dependency_for_capture_program():
AnnotateAdaptiveAvgPool1D: [RemoveRedundancy],
AnnotateQuantAttrs: [
RecomposePixelUnshuffle,
ConvertBmmToMatmul,
RemoveRedundancy,
],
AnnotateStack: [RemoveRedundancy],
AnnotateUnbind: [RemoveRedundancy],
ConvertBmmToMatmul: [RecomposePixelUnshuffle],
DecomposeAny: [RemoveRedundancy],
DecomposeColIm: [FoldQDQ],
DecomposeLinalgVectorNorm: [RemoveRedundancy],
Expand Down
1 change: 1 addition & 0 deletions backends/qualcomm/partition/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@ def get_skip_decomp_table() -> List[torch._ops.OperatorBase]:
torch.ops.aten.instance_norm.default,
torch.ops.aten.leaky_relu.default,
torch.ops.aten.linear.default,
torch.ops.aten.matmul.default,
torch.ops.aten.pixel_shuffle.default,
torch.ops.aten.pixel_unshuffle.default,
torch.ops.aten.prelu.default,
Expand Down
Loading