[Doc] Misc CUDA EP doc changes (#10216)

docs/execution-providers/CUDA-ExecutionProvider.md

@@ -84,6 +84,7 @@ Default value: true
 
 ### cudnn_conv_use_max_workspace
 Check [tuning performance for convolution heavy models](../performance/tune-performance.md#convolution-heavy-models-and-the-cuda-ep) for details on what this flag does.
+This flag is only supported from the V2 version of the provider options struct when used using the C API. The V2 provider options struct can be created using [this](https://onnxruntime.ai/docs/api/c/struct_ort_api.html#a0d29cbf555aa806c050748cf8d2dc172) and updated using [this](https://onnxruntime.ai/docs/api/c/struct_ort_api.html#a4710fc51f75a4b9a75bde20acbfa0783). Please take a look at the sample below for an example.
 
 Default value: 0
 
@@ -112,6 +113,8 @@ session = ort.InferenceSession(model_path, providers=providers)
 
 ### C/C++
 
+#### Using legacy provider options struct
+
 ```c++
 OrtSessionOptions* session_options = /* ... */;
 
@@ -125,3 +128,36 @@ options.do_copy_in_default_stream = 1;
 SessionOptionsAppendExecutionProvider_CUDA(session_options, &options);
 ```
 
+#### Using V2 provider options struct
+
+```c++
+OrtCUDAProviderOptionsV2* cuda_options = nullptr;
+CreateCUDAProviderOptions(&cuda_options);
+
+std::vector<const char*> keys{"device_id", "gpu_mem_limit", "arena_extend_strategy", "cudnn_conv_algo_search", "do_copy_in_default_stream", "cudnn_conv_use_max_workspace"};
+std::vector<const char*> values{"0", "2147483648", "kSameAsRequested", "DEFAULT", "1", "1"};
+
+UpdateCUDAProviderOptions(cuda_options, keys.data(), values.data(), 6);
+
+OrtSessionOptions* session_options = /* ... */;
+SessionOptionsAppendExecutionProvider_CUDA_V2(session_options, cuda_options);
+
+// Finally, don't forget to release the provider options
+ReleaseCUDAProviderOptions(cuda_options);
+```
+
+```c#
+var cudaProviderOptions = new OrtCUDAProviderOptions(); // Dispose this finally
+
+var providerOptionsDict = new Dictionary<string, string>();
+providerOptionsDict["device_id"] = "0";
+providerOptionsDict["gpu_mem_limit"] = "2147483648";
+providerOptionsDict["arena_extend_strategy"] = "kSameAsRequested";
+providerOptionsDict["cudnn_conv_algo_search"] = "DEFAULT";
+providerOptionsDict["do_copy_in_default_stream"] = "1";
+providerOptionsDict["cudnn_conv_use_max_workspace"] = "1";
+
+cudaProviderOptions.UpdateOptions(providerOptionsDict);
+
+SessionOptions options = SessionOptions.MakeSessionOptionWithCudaProvider(cudaProviderOptions);  // Dispose this finally
+```

docs/performance/tune-performance.md

@@ -300,11 +300,35 @@ providers = [("CUDAExecutionProvider", {"cudnn_conv_use_max_workspace": '1'})]
 sess_options = ort.SessionOptions()
 sess = ort.InferenceSession("my_conv_heavy_fp16_model.onnx",  sess_options = sess_options, providers=providers)
 ```
+
 * C/C++
-Support for this provider option will be added in upcoming releases.
+```
+OrtCUDAProviderOptionsV2* cuda_options = nullptr;
+CreateCUDAProviderOptions(&cuda_options);
+
+std::vector<const char*> keys{"cudnn_conv_use_max_workspace"};
+std::vector<const char*> values{"1"};
+
+UpdateCUDAProviderOptions(cuda_options, keys.data(), values.data(), 1);
+
+OrtSessionOptions* session_options = /* ... */;
+SessionOptionsAppendExecutionProvider_CUDA_V2(session_options, cuda_options);
+
+// Finally, don't forget to release the provider options
+ReleaseCUDAProviderOptions(cuda_options);
+```
 
 * C#
-Support for this provider option will be added in upcoming releases.
+```
+var cudaProviderOptions = new OrtCUDAProviderOptions(); // Dispose this finally
+
+var providerOptionsDict = new Dictionary<string, string>();
+providerOptionsDict["cudnn_conv_use_max_workspace"] = "1";
+
+cudaProviderOptions.UpdateOptions(providerOptionsDict);
+
+SessionOptions options = SessionOptions.MakeSessionOptionWithCudaProvider(cudaProviderOptions);  // Dispose this finally
+```
 
 ## Troubleshooting performance issues