Skip to content

Qualcomm AI Engine Direct - Add MHA2SHA pass #15438

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

Qualcomm AI Engine Direct - Add MHA2SHA pass #15438

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1f0c440
Qualcomm AI Engine Direct - Add MHA2SHA pass
shewu-quic Oct 1, 2025
18e7db1
update bc storyllama pte
shewu-quic Oct 29, 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: 2 additions & 0 deletions backends/qualcomm/_passes/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
from .canonicalize_conv import CanonicalizeConv
from .convert_bmm_to_matmul import ConvertBmmToMatmul
from .convert_linear_to_conv2d import ConvertLinearToConv2d
from .convert_mha_to_sha import ConvertMhaToSha
from .convert_square_to_pow import ConvertSquareToPow
from .decompose_any import DecomposeAny
from .decompose_binary_alpha import DecomposeBinaryAlpha
Expand Down Expand Up @@ -55,6 +56,7 @@
CanonicalizeConv,
ConvertBmmToMatmul,
ConvertLinearToConv2d,
ConvertMhaToSha,
ConvertSquareToPow,
DecomposeAny,
DecomposeBinaryAlpha,
Expand Down
9 changes: 0 additions & 9 deletions backends/qualcomm/_passes/canonicalize_conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
import torch

from executorch.backends.qualcomm.builders.utils import get_parameter, set_parameter
from executorch.backends.qualcomm.utils.constants import QCOM_REQUANTIZE
from executorch.exir.pass_base import ExportPass, PassResult
from torch._guards import detect_fake_mode

Expand Down Expand Up @@ -197,14 +196,6 @@ def call(self, graph_module: torch.fx.GraphModule):
)
squeeze_node.meta = copy_meta(node.meta)

if QCOM_REQUANTIZE in input_node.meta:
input_node.meta.pop(QCOM_REQUANTIZE)
if QCOM_REQUANTIZE in node.meta:
squeeze_node.meta[QCOM_REQUANTIZE] = node.meta[
QCOM_REQUANTIZE
]
conv2d_node.meta.pop(QCOM_REQUANTIZE, None)

for user in node.users.copy():
user.replace_input_with(node, squeeze_node)

Expand Down
Loading
Loading