Skip to content

[QNN-EP] Apply Softmax layout transformation for GPU #26233

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
+2 −2
Open

[QNN-EP] Apply Softmax layout transformation for GPU #26233

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
4 changes: 2 additions & 2 deletions onnxruntime/core/providers/qnn/builder/opbuilder/softmax_op_builder.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,7 +152,7 @@ Status SoftmaxOpBuilder::ProcessAttributesAndOutputs(QnnModelWrapper& qnn_model_
std::vector<std::string>&& input_names,
const logging::Logger& logger,
bool do_op_validation) const {
const bool is_npu_backend = IsNpuBackend(qnn_model_wrapper.GetQnnBackendType());
const bool is_qpu_backend = IsQpuBackend(qnn_model_wrapper.GetQnnBackendType());
const std::string& op_type = node_unit.OpType();
const auto& outputs = node_unit.Outputs();
const std::string& orig_output_name = outputs[0].node_arg.Name();
Expand Down Expand Up @@ -202,7 +202,7 @@ Status SoftmaxOpBuilder::ProcessAttributesAndOutputs(QnnModelWrapper& qnn_model_
do_op_validation,
false,
is_graph_output));
} else if (is_npu_backend && axis != static_cast<int32_t>(output_rank) - 1) {
} else if (is_qpu_backend && axis != static_cast<int32_t>(output_rank) - 1) {
std::string transpose_input_name = utils::GetUniqueName(orig_output_name, "_transpose");

std::vector<uint32_t> transpose_input_shape = output_info.shape;
Expand Down