diff --git a/csharp/src/Microsoft.ML.OnnxRuntime/ProviderOptions.shared.cs b/csharp/src/Microsoft.ML.OnnxRuntime/ProviderOptions.shared.cs
index a65839b183..5a4a5dd155 100644
--- a/csharp/src/Microsoft.ML.OnnxRuntime/ProviderOptions.shared.cs
+++ b/csharp/src/Microsoft.ML.OnnxRuntime/ProviderOptions.shared.cs
@@ -58,7 +58,7 @@ namespace Microsoft.ML.OnnxRuntime
///
/// Updates the configuration knobs of OrtTensorRTProviderOptions that will eventually be used to configure a TensorRT EP
/// Please refer to the following on different key/value pairs to configure a TensorRT EP and their meaning:
- /// https://www.onnxruntime.ai/docs/reference/execution-providers/TensorRT-ExecutionProvider.html
+ /// https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html
///
/// key/value pairs used to configure a TensorRT Execution Provider
public void UpdateOptions(Dictionary providerOptions)
@@ -169,7 +169,7 @@ namespace Microsoft.ML.OnnxRuntime
///
/// Updates the configuration knobs of OrtCUDAProviderOptions that will eventually be used to configure a CUDA EP
/// Please refer to the following on different key/value pairs to configure a CUDA EP and their meaning:
- /// https://www.onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html
+ /// https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html
///
/// key/value pairs used to configure a CUDA Execution Provider
public void UpdateOptions(Dictionary providerOptions)
diff --git a/dockerfiles/README.md b/dockerfiles/README.md
index fd418aa189..c198172e8c 100644
--- a/dockerfiles/README.md
+++ b/dockerfiles/README.md
@@ -89,7 +89,7 @@ git submodule update --init
### **1. Using pre-built container images for Python API**
-The unified container image from [Dockerhub](https://hub.docker.com/repository/docker/openvino/onnxruntime_ep_ubuntu20) can be used to run an application on any of the target accelerators. In order to select the target accelerator, the application should explicitly specifiy the choice using the `device_type` configuration option for OpenVINO Execution provider. Refer to [OpenVINO EP runtime configuration documentation](https://www.onnxruntime.ai/docs/reference/execution-providers/OpenVINO-ExecutionProvider.html#summary-of-options) for details on specifying this option in the application code.
+The unified container image from [Dockerhub](https://hub.docker.com/repository/docker/openvino/onnxruntime_ep_ubuntu20) can be used to run an application on any of the target accelerators. In order to select the target accelerator, the application should explicitly specify the choice using the `device_type` configuration option for OpenVINO Execution provider. Refer to [OpenVINO EP runtime configuration documentation](https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#configuration-options) for details on specifying this option in the application code.
If the `device_type` runtime config option is not explicitly specified, CPU will be chosen as the hardware target execution.
### **2. Building from Dockerfile**
diff --git a/docs/onnxruntime_extensions.md b/docs/onnxruntime_extensions.md
index c1f4249433..9f716065e1 100644
--- a/docs/onnxruntime_extensions.md
+++ b/docs/onnxruntime_extensions.md
@@ -24,7 +24,7 @@ ai.onnx.contrib;1;GPT2Tokenizer,
In above operators config, `ai.onnx.contrib` is the domain name of operators in onnxruntime-extensions. We would parse this line to generate required operators in onnxruntime-extensions for build.
### Generate Operators Config
-To generate the **required_operators.config** file from model, please follow the guidance [Converting ONNX models to ORT format](https://onnxruntime.ai/docs/how-to/mobile/model-conversion.html).
+To generate the **required_operators.config** file from model, please follow the guidance [Converting ONNX models to ORT format](https://onnxruntime.ai/docs/reference/ort-format-models.html#convert-onnx-models-to-ort-format).
If your model contains operators from onnxruntime-extensions, please add argument `--custom_op_library` and pass the path to **ortcustomops** shared library built following guidance [share library](https://github.com/microsoft/onnxruntime-extensions#the-share-library-for-non-python).
diff --git a/include/onnxruntime/core/session/onnxruntime_c_api.h b/include/onnxruntime/core/session/onnxruntime_c_api.h
index 09cd8f0f74..fea23de528 100644
--- a/include/onnxruntime/core/session/onnxruntime_c_api.h
+++ b/include/onnxruntime/core/session/onnxruntime_c_api.h
@@ -910,7 +910,7 @@ struct OrtApi {
/** \brief Set the optimization level to apply when loading a graph
*
- * Please see https://www.onnxruntime.ai/docs/resources/graph-optimizations.html for an in-depth explanation
+ * Please see https://onnxruntime.ai/docs/performance/graph-optimizations.html for an in-depth explanation
* \param[in,out] options The session options object
* \param[in] graph_optimization_level The optimization level
*
@@ -2335,7 +2335,7 @@ struct OrtApi {
* Lifetime of the created allocator will be valid for the duration of the environment.
* Returns an error if an allocator with the same ::OrtMemoryInfo is already registered.
*
- * See https://onnxruntime.ai/docs/reference/api/c-api.html for details.
+ * See https://onnxruntime.ai/docs/get-started/with-c.html for details.
*
* \param[in] env ::OrtEnv instance
* \param[in] mem_info
@@ -2663,7 +2663,7 @@ struct OrtApi {
*
* Create the configuration of an arena that can eventually be used to define an arena based allocator's behavior.
*
- * Supported keys are (See https://onnxruntime.ai/docs/reference/api/c-api.html for details on what the
+ * Supported keys are (See https://onnxruntime.ai/docs/get-started/with-c.html for details on what the
* following parameters mean and how to choose these values.):
* "max_mem": Maximum memory that can be allocated by the arena based allocator.
* Use 0 for ORT to pick the best value. Default is 0.
@@ -2819,7 +2819,7 @@ struct OrtApi {
/** \brief Set options in a TensorRT Execution Provider.
*
- * Please refer to https://www.onnxruntime.ai/docs/reference/execution-providers/TensorRT-ExecutionProvider.html#c-api-example
+ * Please refer to https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html#cc
* to know the available keys and values. Key should be in null terminated string format of the member of ::OrtTensorRTProviderOptionsV2
* and value should be its related range.
*
@@ -2880,7 +2880,7 @@ struct OrtApi {
* The behavior of this is exactly the same as OrtApi::CreateAndRegisterAllocator except
* instead of ORT creating an allocator based on provided info, in this case
* ORT uses the user-provided custom allocator.
- * See https://onnxruntime.ai/docs/reference/api/c-api.html for details.
+ * See https://onnxruntime.ai/docs/get-started/with-c.html for details.
*
* \param[in] env
* \param[in] allocator User provided allocator
diff --git a/java/build-android.gradle b/java/build-android.gradle
index ff365ae3d5..a6648c1f6e 100644
--- a/java/build-android.gradle
+++ b/java/build-android.gradle
@@ -32,7 +32,7 @@ def mobileDescription = 'The ONNX Runtime Mobile package is a size optimized inf
'but with reduced disk footprint targeting mobile platforms. To minimize binary size this library supports a ' +
'reduced set of operators and types aligned to typical mobile applications. The ONNX model must be converted to ' +
'ORT format in order to use it with this package. ' +
- 'See https://onnxruntime.ai/docs/reference/ort-model-format.html for more details.'
+ 'See https://onnxruntime.ai/docs/reference/ort-format-models.html for more details.'
def defaultDescription = 'ONNX Runtime is a performance-focused inference engine for ONNX (Open Neural Network ' +
'Exchange) models. This package contains the Android (aar) build of ONNX Runtime. It includes support for all ' +
'types and operators, for ONNX format models. All standard ONNX models can be executed with this package. ' +
diff --git a/js/README.md b/js/README.md
index 2959d42fa1..93715cc6da 100644
--- a/js/README.md
+++ b/js/README.md
@@ -243,7 +243,7 @@ It should be able to consumed by both from projects that uses NPM packages (thro
#### Reduced WebAssembly artifacts
-By default, the WebAssembly artifacts from onnxruntime-web package allows use of both standard ONNX models (.onnx) and ORT format models (.ort). There is an option to use a minimal build of ONNX Runtime to reduce the binary size, which only supports ORT format models. See also [ORT format model](https://onnxruntime.ai/docs/tutorials/mobile/overview.html) for more information.
+By default, the WebAssembly artifacts from onnxruntime-web package allows use of both standard ONNX models (.onnx) and ORT format models (.ort). There is an option to use a minimal build of ONNX Runtime to reduce the binary size, which only supports ORT format models. See also [ORT format model](https://onnxruntime.ai/docs/reference/ort-format-models.html) for more information.
#### Reduced JavaScript bundle file fize
diff --git a/objectivec/include/ort_enums.h b/objectivec/include/ort_enums.h
index 040b50f2c3..e82765b535 100644
--- a/objectivec/include/ort_enums.h
+++ b/objectivec/include/ort_enums.h
@@ -41,7 +41,7 @@ typedef NS_ENUM(int32_t, ORTTensorElementDataType) {
/**
* The ORT graph optimization levels.
* See here for more details:
- * https://www.onnxruntime.ai/docs/resources/graph-optimizations.html
+ * https://onnxruntime.ai/docs/performance/graph-optimizations.html
*/
typedef NS_ENUM(int32_t, ORTGraphOptimizationLevel) {
ORTGraphOptimizationLevelNone,
diff --git a/onnxruntime/python/onnxruntime_pybind_state.cc b/onnxruntime/python/onnxruntime_pybind_state.cc
index dd24ce51e1..8c1ebf9cf2 100644
--- a/onnxruntime/python/onnxruntime_pybind_state.cc
+++ b/onnxruntime/python/onnxruntime_pybind_state.cc
@@ -534,11 +534,11 @@ std::unique_ptr CreateExecutionProviderInstance(
return cuda_provider_info->CreateExecutionProviderFactory(info)->CreateProvider();
} else {
if (!Env::Default().GetEnvironmentVar("CUDA_PATH").empty()) {
- ORT_THROW("CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.");
+ ORT_THROW("CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.");
}
}
}
- LOGS_DEFAULT(WARNING) << "Failed to create " << type << ". Please reference https://onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#requirements to ensure all dependencies are met.";
+ LOGS_DEFAULT(WARNING) << "Failed to create " << type << ". Please reference https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements to ensure all dependencies are met.";
#endif
} else if (type == kRocmExecutionProvider) {
#ifdef USE_ROCM
diff --git a/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb b/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb
index a769fc12ae..74b81fc7c8 100644
--- a/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb
+++ b/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb
@@ -45,7 +45,7 @@
"```\n",
"Finally, launch Jupyter Notebook and you can choose gpu_env as kernel to run this notebook.\n",
"\n",
- "Onnxruntime-gpu need specified version of CUDA and cuDNN. You can find the Requirements [here]( http://www.onnxruntime.ai/docs/how-to/install.html). Remember to add the directories to PATH environment variable (See [CUDA and cuDNN Path](#CUDA-and-cuDNN-Path) below)."
+ "Onnxruntime-gpu need specified version of CUDA and cuDNN. You can find the Requirements [here](https://onnxruntime.ai/docs/install/). Remember to add the directories to PATH environment variable (See [CUDA and cuDNN Path](#CUDA-and-cuDNN-Path) below)."
]
},
{
@@ -348,7 +348,7 @@
"## 4. Inference ONNX Model with ONNX Runtime ##\n",
"\n",
"### CUDA and cuDNN Path\n",
- "onnxruntime-gpu has dependency on [CUDA](https://developer.nvidia.com/cuda-downloads) and [cuDNN](https://developer.nvidia.com/cudnn). Required CUDA version can be found [here](http://www.onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#requirements)\n"
+ "onnxruntime-gpu has dependency on [CUDA](https://developer.nvidia.com/cuda-downloads) and [cuDNN](https://developer.nvidia.com/cudnn). Required CUDA version can be found [here](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements)\n"
]
},
{
diff --git a/onnxruntime/python/tools/transformers/optimizer.py b/onnxruntime/python/tools/transformers/optimizer.py
index 65de1bf770..02a2db2170 100644
--- a/onnxruntime/python/tools/transformers/optimizer.py
+++ b/onnxruntime/python/tools/transformers/optimizer.py
@@ -197,7 +197,7 @@ def optimize_model(
):
"""Optimize Model by OnnxRuntime and/or python fusion logic.
- ONNX Runtime has graph optimizations (https://onnxruntime.ai/docs/resources/graph-optimizations.html).
+ ONNX Runtime has graph optimizations (https://onnxruntime.ai/docs/performance/graph-optimizations.html).
However, the coverage is limited. We also have graph fusions that implemented in Python to improve the coverage.
They can combined: ONNX Runtime will run first when opt_level > 0, then graph fusions in Python will be applied.
diff --git a/tools/ci_build/reduce_op_kernels.py b/tools/ci_build/reduce_op_kernels.py
index e2cf598136..47e7d5b154 100755
--- a/tools/ci_build/reduce_op_kernels.py
+++ b/tools/ci_build/reduce_op_kernels.py
@@ -325,7 +325,7 @@ if __name__ == "__main__":
type=str,
help="Path to configuration file. "
"Create with /tools/python/create_reduced_build_config.py and edit if needed. "
- "See https://onnxruntime.ai/docs/reference/reduced-operator-config-file.html for more "
+ "See https://onnxruntime.ai/docs/reference/operators/reduced-operator-config-file.html for more "
"information.",
)
diff --git a/tools/python/util/mobile_helpers/check_model_can_use_ort_mobile_pkg.py b/tools/python/util/mobile_helpers/check_model_can_use_ort_mobile_pkg.py
index f58a25b64a..6b9ea89148 100644
--- a/tools/python/util/mobile_helpers/check_model_can_use_ort_mobile_pkg.py
+++ b/tools/python/util/mobile_helpers/check_model_can_use_ort_mobile_pkg.py
@@ -236,7 +236,7 @@ def run_check_with_model(
if unsupported:
logger.info("\nModel is not supported by the pre-built package due to unsupported types and/or operators.")
logger.info(
- "Please see https://onnxruntime.ai/docs/reference/mobile/prebuilt-package/ for information "
+ "Please see https://onnxruntime.ai/docs/install/#install-on-web-and-mobile for information "
"on what is supported in the pre-built package."
)
logger.info(