1.16.3 patch release (#18491)

Cherry-pick the following PRs:

#18467 
#17797
#18341
#18456

.lintrunner.toml

@@ -97,33 +97,6 @@ init_command = [
 ]
 is_formatter = true
 
-[[linter]]
-code = 'PYLINT'
-include_patterns = [
-    # TODO: Opt in to pylint by adding paths here
-]
-exclude_patterns = [
-]
-command = [
-    'python',
-    '-m',
-    'lintrunner_adapters',
-    'run',
-    'pylint_linter',
-    '--rcfile=pyproject.toml',
-    '--',
-    '@{{PATHSFILE}}'
-]
-init_command = [
-    'python',
-    '-m',
-    'lintrunner_adapters',
-    'run',
-    'pip_init',
-    '--dry-run={{DRYRUN}}',
-    '--requirement=requirements-lintrunner.txt',
-]
-
 [[linter]]
 code = 'RUSTFMT'
 include_patterns = ['**/*.rs']

VERSION_NUMBER

@@ -1 +1 @@
-1.16.2
+1.16.3

docs/python/README.rst

@@ -8,6 +8,11 @@ For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://ak
 Changes
 -------
 
+1.16.3
+^^^^^^
+
+Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.16.3
+
 1.16.2
 ^^^^^^
 

include/onnxruntime/core/platform/EigenNonBlockingThreadPool.h

@@ -278,7 +278,7 @@ class ThreadPoolProfiler {
   int num_threads_;
 #ifdef _MSC_VER
 #pragma warning(push)
-// C4324: structure was padded due to alignment specifier
+  // C4324: structure was padded due to alignment specifier
 #pragma warning(disable : 4324)
 #endif  // _MSC_VER
   struct ORT_ALIGN_TO_AVOID_FALSE_SHARING ChildThreadStat {

js/common/lib/version.ts

@@ -4,4 +4,4 @@
 // This file is generated by /js/scripts/update-version.ts
 // Do not modify file content manually.
 
-export const version = '1.16.2';
+export const version = '1.16.3';

js/common/package.json

@@ -2,7 +2,7 @@
   "license": "MIT",
   "type": "module",
   "name": "onnxruntime-common",
-  "version": "1.16.2",
+  "version": "1.16.3",
   "repository": {
     "url": "https://github.com/Microsoft/onnxruntime.git",
     "type": "git"

js/node/lib/version.ts

@@ -4,4 +4,4 @@
 // This file is generated by /js/scripts/update-version.ts
 // Do not modify file content manually.
 
-export const version = '1.16.2';
+export const version = '1.16.3';

js/node/package.json

@@ -13,7 +13,7 @@
       3
     ]
   },
-  "version": "1.16.2",
+  "version": "1.16.3",
   "dependencies": {
     "onnxruntime-common": "file:../common"
   },

js/react_native/lib/version.ts

@@ -4,4 +4,4 @@
 // This file is generated by /js/scripts/update-version.ts
 // Do not modify file content manually.
 
-export const version = '1.16.2';
+export const version = '1.16.3';

js/react_native/package.json

@@ -36,7 +36,7 @@
     "registry": "https://registry.npmjs.org/"
   },
   "source": "lib/index",
-  "version": "1.16.2",
+  "version": "1.16.3",
   "main": "dist/commonjs/index",
   "homepage": "https://github.com/microsoft/onnxruntime/blob/main/js/react_native/README.md",
   "files": [

js/react_native/yarn.lock

@@ -5188,7 +5188,7 @@ onetime@^5.1.0, onetime@^5.1.2:
     mimic-fn "^2.1.0"
 
 "onnxruntime-common@file:../common":
-  version "1.16.2"
+  version "1.16.3"
 
 open@^6.2.0:
   version "6.4.0"

js/web/lib/version.ts

@@ -4,4 +4,4 @@
 // This file is generated by /js/scripts/update-version.ts
 // Do not modify file content manually.
 
-export const version = '1.16.2';
+export const version = '1.16.3';

js/web/package.json

@@ -8,7 +8,7 @@
     "type": "git"
   },
   "author": "fs-eire",
-  "version": "1.16.2",
+  "version": "1.16.3",
   "jsdelivr": "dist/ort.min.js",
   "dependencies": {
     "flatbuffers": "^1.12.0",

onnxruntime/__init__.py

@@ -7,7 +7,7 @@
 For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://aka.ms/onnxruntime/>`_
 or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
 """
-__version__ = "1.16.2"
+__version__ = "1.16.3"
 __author__ = "Microsoft"
 
 # we need to do device version validation (for example to check Cuda version for an onnxruntime-training package).

onnxruntime/core/framework/session_state_utils.cc

@@ -455,11 +455,10 @@ common::Status SaveInputOutputNamesToNodeMapping(const onnxruntime::GraphViewer&
   // utils::CopyOneInputAcrossDevices is happy.
 
   auto& input_map = session_state.GetInputNodeInfoMap();
-  auto end_map = input_map.cend();
 
   for (const auto& graph_input : graph_inputs) {
     const auto& name = graph_input->Name();
-    if (input_map.find(name) == end_map) {
+    if (input_map.find(name) == input_map.cend()) {
       // dummy entry for an input that we didn't find a use of in the graph. log it in case that's a bug.
       // utils::CopyOneInputAcrossDevices will use the input OrtValue as is given we don't believe it's used anywhere.
       LOGS(session_state.Logger(), INFO) << (graph.IsSubgraph() ? "Subgraph" : "Graph") << " input with name "

onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc

@@ -1126,6 +1126,11 @@ TensorrtExecutionProvider::~TensorrtExecutionProvider() {
     }
   }
 
+  if (external_stream_) {
+    ORT_IGNORE_RETURN_VALUE(CUBLAS_CALL(cublasDestroy(external_cublas_handle_)));
+    ORT_IGNORE_RETURN_VALUE(CUDNN_CALL(cudnnDestroy(external_cudnn_handle_)));
+  }
+
   if (!external_stream_ && stream_) {
     ORT_IGNORE_RETURN_VALUE(CUDA_CALL(cudaStreamDestroy(stream_)));
   }

onnxruntime/core/session/onnxruntime_c_api.cc

@@ -2744,7 +2744,7 @@ static_assert(offsetof(OrtApi, GetBuildInfoString) / sizeof(void*) == 254, "Size
 static_assert(offsetof(OrtApi, KernelContext_GetResource) / sizeof(void*) == 265, "Size of version 16 API cannot change");
 
 // So that nobody forgets to finish an API version, this check will serve as a reminder:
-static_assert(std::string_view(ORT_VERSION) == "1.16.2",
+static_assert(std::string_view(ORT_VERSION) == "1.16.3",
               "ORT_Version change detected, please follow below steps to ensure OrtApi is updated properly");
 // 1. Update the hardcoded version string in above static_assert to silence it
 // 2. If there were any APIs added to ort_api_1_to_16 above:

onnxruntime/python/backend/backend.py

@@ -63,7 +63,7 @@ def is_opset_supported(cls, model):
                         error_message = (
                             "Skipping this test as only released onnx opsets are supported."
                             "To run this test set env variable ALLOW_RELEASED_ONNX_OPSET_ONLY to 0."
-                            " Got Domain '{}' version '{}'.".format(domain, opset.version)
+                            f" Got Domain '{domain}' version '{opset.version}'."
                         )
                         return False, error_message
                 except AttributeError:
@@ -74,7 +74,7 @@ def is_opset_supported(cls, model):
                         error_message = (
                             "Skipping this test as only released onnx opsets are supported."
                             "To run this test set env variable ALLOW_RELEASED_ONNX_OPSET_ONLY to 0."
-                            " Got Domain '{}' version '{}'.".format(domain, opset.version)
+                            f" Got Domain '{domain}' version '{opset.version}'."
                         )
                         return False, error_message
         return True, ""

onnxruntime/python/tools/onnxruntime_test.py

@@ -40,7 +40,7 @@ def generate_feeds(sess, symbolic_dims: dict | None = None):
             if not dim:
                 # unknown dim
                 shape.append(1)
-            elif type(dim) == str:
+            elif isinstance(dim, str):
                 # symbolic dim. see if we have a value otherwise use 1
                 if dim in symbolic_dims:
                     shape.append(int(symbolic_dims[dim]))

onnxruntime/python/tools/profile_explorer/profile_explorer.py

@@ -82,8 +82,8 @@ def _shape_to_string(shape):
     for dict_obj in shape:
         if len(dict_obj) > 1:
             raise ValueError("Unhandled type in _shape_to_string()")
-        key = list(dict_obj.keys())[0]
-        value = list(dict_obj.values())[0]
+        key = next(iter(dict_obj.keys()))
+        value = next(iter(dict_obj.values()))
         if len(res) != 0:
             res += ","
         res += f'{key}({"x".join(str(v) for v in value)})'

onnxruntime/python/tools/quantization/calibrate.py

@@ -363,9 +363,9 @@ def compute_data(self) -> TensorsData:
             else:
                 min_value_array = min(merged_added_output_dict[added_output_names[i]])
                 max_value_array = max(merged_added_output_dict[added_output_names[i + 1]])
-            if type(min_value_array) == int or min_value_array.size > 0:
+            if isinstance(min_value_array, int) or min_value_array.size > 0:
                 min_value = float(min_value_array)
-            if type(max_value_array) == int or max_value_array.size > 0:
+            if isinstance(max_value_array, int) or max_value_array.size > 0:
                 max_value = float(max_value_array)
 
             if self.symmetric:

onnxruntime/python/tools/quantization/onnx_quantizer.py

@@ -597,7 +597,7 @@ def _get_quantization_params(self, param_name, use_scale=None, use_zeropoint=Non
             if params is None or len(params) != 2:
                 raise ValueError(
                     "Quantization parameters should contain zero point and scale. "
-                    "Specified values for output {}: {}".format(param_name, params)
+                    f"Specified values for output {param_name}: {params}"
                 )
 
             zero_point_values = [params["zero_point"]]