Enable adaptive stripping and eliminate dependency of weight sharing feature on OVEP qdq stripping (#629)

* eliminate dependency of weight sharing on ovep qdq stripping pass

* fix qdqnodeunit issue

* enable compiler stripping

* enable adaptive stripping: cleanup code

* fix backward compatibility issue

* add logs to identify which stripping is enabled

* address PR review comments

* fix unused variable error

* resolve unused var issue

* fix CI issues

Author: saurabhkale17

onnxruntime/core/providers/openvino/backend_manager.cc

@@ -20,6 +20,7 @@
 #include "core/providers/openvino/ov_interface.h"
 #include "core/providers/openvino/ov_versions/capability.h"
 #include "core/providers/openvino/qdq_transformations/qdq_stripping.h"
+#include "core/providers/openvino/ov_interface.h"
 
 namespace onnxruntime {
 namespace openvino_ep {
@@ -384,7 +385,7 @@ BackendManager::GetModelProtoFromFusedNode(const onnxruntime::Node& fused_node,
   if (session_context_.device_type.find("NPU") != std::string::npos &&
       (enable_ovep_qdq_optimizer || session_context_.so_share_ep_contexts)) {
     std::unique_ptr<onnxruntime::Model> model;
-    Status status = CreateModelWithStrippedQDQNodes(subgraph, logger, session_context_.so_share_ep_contexts, enable_ovep_qdq_optimizer, model, shared_context_.shared_weights);
+    Status status = CreateModelWithStrippedQDQNodes(subgraph, logger, session_context_.so_share_ep_contexts, model, shared_context_.shared_weights, enable_ovep_qdq_optimizer);
     auto model_proto = model->ToProto();
     model_proto->set_ir_version(ONNX_NAMESPACE::Version::IR_VERSION);
     print_model_proto_duration();

onnxruntime/core/providers/openvino/ov_interface.cc

@@ -46,6 +46,17 @@ void printDebugInfo(const ov::CompiledModel& obj) {
 }
 #endif
 
+// Function to check if a given OV property is enabled
+std::optional<bool> queryOVProperty(const std::string& property, const std::string& device_type) {
+  try {
+      // Get the property value
+      auto supported_properties = OVCore::Get()->core.get_property(device_type, ov::supported_properties);
+      return std::find(supported_properties.begin(), supported_properties.end(), property) != supported_properties.end();
+  } catch (const std::exception&) {
+      return std::nullopt; // Property not found or invalid
+  }
+}
+
 std::shared_ptr<OVNetwork> OVCore::ReadModel(std::string&& model, const std::string& model_path) {
   try {
     std::istringstream modelStringStream(std::move(model));

onnxruntime/core/providers/openvino/qdq_transformations/qdq_stripping.cc

@@ -449,8 +449,8 @@ static bool HandleDoubleQDQ(onnxruntime::Graph& dst_graph, const onnxruntime::Gr
 static void AddStandaloneNodeUnit(onnxruntime::Graph& dst_graph, const onnxruntime::GraphViewer& src_graph,
                                   const NodeUnit& node_unit,
                                   std::set<std::string>& initializers_to_keep,
-                                  bool IsWeightSharingWithoutOVEPQDQStripping,
-                                  const logging::Logger& /* logger */) {
+                                  const logging::Logger& /* logger */,
+                                  bool IsWeightSharingWithoutOVEPQDQStripping) {
   assert(node_unit.UnitType() == NodeUnit::Type::SingleNode);
 
   // this is the scenario where WAI is enabled and ovep stripping is disabled
@@ -521,8 +521,8 @@ static void AddQDQNodeUnit(onnxruntime::Graph& dst_graph,
                            const onnxruntime::GraphViewer& src_graph,
                            const NodeUnit& node_unit,
                            std::set<std::string>& initializers_to_keep,
-                           bool IsWeightSharingWithoutOVEPQDQStripping,
-                           const logging::Logger& /* logger */) {
+                           const logging::Logger& /* logger */,
+                           bool IsWeightSharingWithoutOVEPQDQStripping) {
   assert(node_unit.UnitType() == NodeUnit::Type::QDQGroup);
 
   // Collect inputs coming into the node unit.
@@ -683,7 +683,8 @@ Status CreateModelWithStrippedQDQNodes(const GraphViewer& src_graph,
                                        bool enable_ovep_weight_sharing,
                                        bool enable_ovep_qdq_optimizer,
                                        /*out*/ std::unique_ptr<onnxruntime::Model>& model,
-                                       /*out*/ sw& shared_weights) {
+                                       /*out*/ sw& shared_weights,
+                                       bool enable_ovep_qdq_optimizer) {
   // NOTE: This function is a re-implementation of GraphViewerToProto() in core/graph/graph_proto_serializer.cc
   // with the following differences:
   //   - Uses onnxruntime::Graph APIs instead of onnx::GraphProto APIs.
@@ -777,9 +778,9 @@ Status CreateModelWithStrippedQDQNodes(const GraphViewer& src_graph,
     bool IsWeightSharingWithoutOVEPQDQStripping = enable_ovep_weight_sharing && !enable_ovep_qdq_optimizer;
 
     if (node_unit->UnitType() == NodeUnit::Type::SingleNode) {
-      AddStandaloneNodeUnit(dst_graph, src_graph, *node_unit, initializers_to_keep, IsWeightSharingWithoutOVEPQDQStripping, logger);
+      AddStandaloneNodeUnit(dst_graph, src_graph, *node_unit, initializers_to_keep, logger, IsWeightSharingWithoutOVEPQDQStripping);
     } else {
-      AddQDQNodeUnit(dst_graph, src_graph, *node_unit, initializers_to_keep, IsWeightSharingWithoutOVEPQDQStripping, logger);
+      AddQDQNodeUnit(dst_graph, src_graph, *node_unit, initializers_to_keep, logger, IsWeightSharingWithoutOVEPQDQStripping);
     }
 
     seen_node_units.insert(node_unit);

onnxruntime/core/providers/openvino/qdq_transformations/qdq_stripping.h

@@ -18,7 +18,8 @@ Status CreateModelWithStrippedQDQNodes(const GraphViewer& src_graph,
                                        bool enable_ovep_weight_sharing,
                                        bool enable_ovep_qdq_optimizer,
                                        /*out*/ std::unique_ptr<onnxruntime::Model>& model,
-                                       /*out*/ sw& shared_weights);
+                                       /*out*/ sw& shared_weights,
+                                       bool enable_ovep_qdq_optimizer);
 
 bool dumpMetaDataMapToBinary(const sw::Metadata::Map& shared_weights, const std::string& filename);
 }  // namespace openvino_ep