From a363196f44bac19a3a8e9b10d68050800b95235e Mon Sep 17 00:00:00 2001 From: Yifan Li <109183385+yf711@users.noreply.github.com> Date: Wed, 29 Jan 2025 11:38:11 -0800 Subject: [PATCH] [TensorRT EP] Update trt link (#23532) --- docs/build/eps.md | 2 +- .../TensorRT-ExecutionProvider.md | 12 ++++++------ docs/tutorials/csharp/csharp-gpu.md | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/build/eps.md b/docs/build/eps.md index a3b33d0587124..24f276b3379a2 100644 --- a/docs/build/eps.md +++ b/docs/build/eps.md @@ -109,7 +109,7 @@ See more information on the TensorRT Execution Provider [here](../execution-prov {: .no_toc } * Follow [instructions for CUDA execution provider](#cuda) to install CUDA and cuDNN, and setup environment variables. - * Follow [instructions for installing TensorRT](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html) + * Follow [instructions for installing TensorRT](https://docs.nvidia.com/deeplearning/tensorrt/latest/installing-tensorrt/installing.html) * The TensorRT execution provider for ONNX Runtime is built and tested with TensorRT 10.0. * The path to TensorRT installation must be provided via the `--tensorrt_home` parameter. * ONNX Runtime uses TensorRT built-in parser from `tensorrt_home` by default. diff --git a/docs/execution-providers/TensorRT-ExecutionProvider.md b/docs/execution-providers/TensorRT-ExecutionProvider.md index 0c853884a4060..667c9d6d929ec 100644 --- a/docs/execution-providers/TensorRT-ExecutionProvider.md +++ b/docs/execution-providers/TensorRT-ExecutionProvider.md @@ -417,14 +417,14 @@ TensorRT configurations can be set by execution provider options. It's useful wh * Description: control if sparsity can be used by TRT. - * Check `--sparsity` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags). + * Check `--sparsity` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/latest/reference/command-line-programs.html#commonly-used-command-line-flags). ##### trt_builder_optimization_level * Description: set the builder optimization level. - > WARNING: levels below 3 do not guarantee good engine performance, but greatly improve build time. Default 3, valid range [0-5]. Check `--builderOptimizationLevel` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags). + > WARNING: levels below 3 do not guarantee good engine performance, but greatly improve build time. Default 3, valid range [0-5]. Check `--builderOptimizationLevel` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/latest/reference/command-line-programs.html#commonly-used-command-line-flags). ##### trt_auxiliary_streams @@ -432,7 +432,7 @@ TensorRT configurations can be set by execution provider options. It's useful wh * Description: set maximum number of auxiliary streams per inference stream. * Setting this value to 0 will lead to optimal memory usage. * Default -1 = heuristics. - * Check `--maxAuxStreams` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags). + * Check `--maxAuxStreams` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/latest/reference/command-line-programs.html#commonly-used-command-line-flags). ##### trt_tactic_sources @@ -519,11 +519,11 @@ Following environment variables can be set for TensorRT execution provider. Clic * `ORT_TENSORRT_BUILD_HEURISTICS_ENABLE`: Build engine using heuristics to reduce build time. Default 0 = false, nonzero = true. -* `ORT_TENSORRT_SPARSITY_ENABLE`: Control if sparsity can be used by TRT. Default 0 = false, 1 = true. Check `--sparsity` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags). +* `ORT_TENSORRT_SPARSITY_ENABLE`: Control if sparsity can be used by TRT. Default 0 = false, 1 = true. Check `--sparsity` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/latest/reference/command-line-programs.html#commonly-used-command-line-flags). -* `ORT_TENSORRT_BUILDER_OPTIMIZATION_LEVEL`: Set the builder optimization level. WARNING: levels below 3 do not guarantee good engine performance, but greatly improve build time. Default 3, valid range [0-5]. Check `--builderOptimizationLevel` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags). +* `ORT_TENSORRT_BUILDER_OPTIMIZATION_LEVEL`: Set the builder optimization level. WARNING: levels below 3 do not guarantee good engine performance, but greatly improve build time. Default 3, valid range [0-5]. Check `--builderOptimizationLevel` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/latest/reference/command-line-programs.html#commonly-used-command-line-flags). -* `ORT_TENSORRT_AUXILIARY_STREAMS`: Set maximum number of auxiliary streams per inference stream. Setting this value to 0 will lead to optimal memory usage. Default -1 = heuristics. Check `--maxAuxStreams` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags). +* `ORT_TENSORRT_AUXILIARY_STREAMS`: Set maximum number of auxiliary streams per inference stream. Setting this value to 0 will lead to optimal memory usage. Default -1 = heuristics. Check `--maxAuxStreams` in `trtexec` command-line flags for [details](https://docs.nvidia.com/deeplearning/tensorrt/latest/reference/command-line-programs.html#commonly-used-command-line-flags). * `ORT_TENSORRT_TACTIC_SOURCES`: Specify the tactics to be used by adding (+) or removing (-) tactics from the default tactic sources (default = all available tactics) e.g. "-CUDNN,+CUBLAS" available keys: "CUBLAS", "CUBLAS_LT", "CUDNN" or "EDGE_MASK_CONVOLUTIONS". diff --git a/docs/tutorials/csharp/csharp-gpu.md b/docs/tutorials/csharp/csharp-gpu.md index 3f62fdd649781..17668fdd76d13 100644 --- a/docs/tutorials/csharp/csharp-gpu.md +++ b/docs/tutorials/csharp/csharp-gpu.md @@ -31,7 +31,7 @@ See this table for supported versions: NOTE: Full table can be found [here](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements) -- Follow section [2. Installing cuDNN on Windows](https://docs.nvidia.com/deeplearning/cudnn/installation/windows.html). NOTE: Skip step 5 in section 2.3 on updating Visual Studio settings, this is only for C++ projects. +- Follow section [2. Installing cuDNN on Windows](https://docs.nvidia.com/deeplearning/cudnn/installation/latest/windows.html). NOTE: Skip step 5 in section 2.3 on updating Visual Studio settings, this is only for C++ projects. - Restart your computer and verify the installation by running the following command or in python with PyTorch: