Update range of gpu arch (#23309)

### Description
<!-- Describe your changes. -->
* Remove deprecated gpu arch to control nuget/python package size
(latest TRT supports sm75 Turing and newer arch)
* Add 90 to support blackwell series in next release (86;89 not
considered as adding them will rapidly increase package size)

| arch_range | Python-cuda12 | Nuget-cuda12 |
| -------------- |
------------------------------------------------------------ |
---------------------------------- |
| 60;61;70;75;80 | Linux: 279MB Win: 267MB | Linux: 247MB Win: 235MB |
| 75;80 | Linux: 174MB Win: 162MB | Linux: 168MB Win: 156MB |
| **75;80;90** | **Linux: 299MB Win: 277MB** | **Linux: 294MB Win:
271MB** |
| 75;80;86;89 | [Linux: MB Win:
390MB](https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=647457&view=results)
| Linux: 416MB Win: 383MB |
| 75;80;86;89;90 | [Linux: MB Win:
505MB](https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=646536&view=results)
| Linux: 541MB Win: 498MB |

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Callout: While adding sm90 support, the build of cuda11.8+cudnn8 will be
dropped in the coming ORT release,
as the build has issue with blackwell (mentioned in comments) and demand
on cuda 11 is minor, according to internal ort-cuda11 repo.

Author: yf711

dockerfiles/Dockerfile.cuda

@@ -12,7 +12,9 @@ ARG OS=ubuntu24.04
 FROM nvcr.io/nvidia/cuda:${CUDA_VERSION}-devel-${OS}
 ARG CUDA_VERSION
 ARG CUDNN_VERSION
-ARG CMAKE_CUDA_ARCHITECTURES="61;70;75;80;86;90"
+# Adjust as needed 
+# Check your CUDA arch: https://developer.nvidia.com/cuda-gpus
+ARG CMAKE_CUDA_ARCHITECTURES="75;80;90"
 
 ENV DEBIAN_FRONTEND=noninteractive
 

dockerfiles/Dockerfile.tensorrt

@@ -10,7 +10,9 @@ FROM nvcr.io/nvidia/tensorrt:${TRT_CONTAINER_VERSION}-py3
 
 ARG ONNXRUNTIME_REPO=https://github.com/Microsoft/onnxruntime
 ARG ONNXRUNTIME_BRANCH=main
-ARG CMAKE_CUDA_ARCHITECTURES=37;50;52;60;61;70;75;80
+# Adjust as needed 
+# Check your CUDA arch: https://developer.nvidia.com/cuda-gpus
+ARG CMAKE_CUDA_ARCHITECTURES=75;80;90
 
 RUN apt-get update &&\
     apt-get install -y sudo git bash unattended-upgrades

tools/ci_build/github/azure-pipelines/stages/nuget-win-cuda-packaging-stage.yml

@@ -50,7 +50,7 @@ stages:
     msbuildPlatform: x64
     packageName: x64-cuda
     CudaVersion: ${{ parameters.CudaVersion }}
-    buildparameter: --use_cuda --cuda_home=${{ parameters.win_cuda_home }} --enable_onnx_tests --enable_wcos --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=60;61;70;75;80"
+    buildparameter: --use_cuda --cuda_home=${{ parameters.win_cuda_home }} --enable_onnx_tests --enable_wcos --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=75;80;90"
     runTests: ${{ parameters.RunOnnxRuntimeTests }}
     buildJava: ${{ parameters.buildJava }}
     java_artifact_id: onnxruntime_gpu
@@ -68,7 +68,7 @@ stages:
     msbuildPlatform: x64
     CudaVersion: ${{ parameters.CudaVersion }}
     packageName: x64-tensorrt
-    buildparameter: --use_tensorrt --tensorrt_home=${{ parameters.win_trt_home }} --cuda_home=${{ parameters.win_cuda_home }}  --enable_onnx_tests --enable_wcos --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=60;61;70;75;80"
+    buildparameter: --use_tensorrt --tensorrt_home=${{ parameters.win_trt_home }} --cuda_home=${{ parameters.win_cuda_home }}  --enable_onnx_tests --enable_wcos --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=75;80;90"
     runTests: ${{ parameters.RunOnnxRuntimeTests }}
     buildJava: ${{ parameters.buildJava }}
     java_artifact_id: onnxruntime_gpu

tools/ci_build/github/azure-pipelines/stages/py-gpu-packaging-stage.yml

@@ -56,7 +56,7 @@ stages:
           PYTHON_VERSION: ${{ python_version }}
           EP_NAME: gpu
           CudaVersion: ${{ parameters.cuda_version }}
-          EP_BUILD_FLAGS: --enable_lto --cuda_home=$(Agent.TempDirectory)\v${{ parameters.cuda_version }} --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=52;60;61;70;75;80"
+          EP_BUILD_FLAGS: --enable_lto --cuda_home=$(Agent.TempDirectory)\v${{ parameters.cuda_version }} --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=75;80;90"
           use_tensorrt: True
 
   - ${{ if eq(parameters.enable_linux_cuda, true) }}:

tools/ci_build/github/azure-pipelines/templates/py-packaging-selectable-stage.yml

@@ -319,7 +319,7 @@ stages:
                   --build_wheel \
                   --enable_onnx_tests --use_tensorrt --cuda_version=11.8 --tensorrt_home=/usr --cuda_home=/usr/local/cuda-11.8 --cudnn_home=/usr/local/cuda-11.8 \
                   ${{ parameters.gpu_build_py_parameters }} \
-                  --cmake_extra_defines CMAKE_CUDA_HOST_COMPILER=/opt/rh/devtoolset-11/root/usr/bin/cc 'CMAKE_CUDA_ARCHITECTURES=37;50;52;60;61;70;75;80'
+                  --cmake_extra_defines CMAKE_CUDA_HOST_COMPILER=/opt/rh/devtoolset-11/root/usr/bin/cc 'CMAKE_CUDA_ARCHITECTURES=75;80;90'
           workingDirectory: $(Build.SourcesDirectory)
 
       - task: CmdLine@2
@@ -349,7 +349,7 @@ stages:
                   --build_wheel \
                   --enable_onnx_tests --use_tensorrt --cuda_version=11.8 --tensorrt_home=/usr --cuda_home=/usr/local/cuda-11.8 --cudnn_home=/usr/local/cuda-11.8  \
                   ${{ parameters.gpu_build_py_parameters }} --ctest_path '' \
-                  --cmake_extra_defines CMAKE_CUDA_HOST_COMPILER=/opt/rh/devtoolset-11/root/usr/bin/cc 'CMAKE_CUDA_ARCHITECTURES=37;50;52;60;61;70;75;80'
+                  --cmake_extra_defines CMAKE_CUDA_HOST_COMPILER=/opt/rh/devtoolset-11/root/usr/bin/cc 'CMAKE_CUDA_ARCHITECTURES=75;80;90'
 
       - task: CopyFiles@2
         displayName: 'Copy Python Wheel to: $(Build.ArtifactStagingDirectory)'
@@ -379,7 +379,7 @@ stages:
       - template: common-variables.yml
         CUDA_VERSION: '11.8'
         buildArch: x64
-        EpBuildFlags: --use_tensorrt --tensorrt_home="$(Agent.TempDirectory)\${{ variables.win_trt_folder_cuda11 }}" --cuda_version=$(CUDA_VERSION) --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v$(CUDA_VERSION)" --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=37;50;52;60;61;70;75;80"
+        EpBuildFlags: --use_tensorrt --tensorrt_home="$(Agent.TempDirectory)\${{ variables.win_trt_folder_cuda11 }}" --cuda_version=$(CUDA_VERSION) --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v$(CUDA_VERSION)" --cmake_extra_defines "CMAKE_CUDA_ARCHITECTURES=75;80;90"
         EnvSetupScript: setup_env_gpu.bat
         EP_NAME: gpu
         VSGenerator: 'Visual Studio 17 2022'

tools/ci_build/github/linux/build_cuda_c_api_package.sh

@@ -2,4 +2,4 @@
 set -e -x
 docker run --rm --volume \
 $BUILD_SOURCESDIRECTORY:/onnxruntime_src --volume $BUILD_BINARIESDIRECTORY:/build -e NIGHTLY_BUILD onnxruntimecuda${CUDA_VERSION_MAJOR}build \
-/bin/bash -c "/usr/bin/python3.12 /onnxruntime_src/tools/ci_build/build.py --enable_lto --build_java --build_nodejs --build_dir /build --config Release --skip_submodule_sync  --parallel --use_binskim_compliant_compile_flags --build_shared_lib --use_cuda --cuda_version=$CUDA_VERSION --cuda_home=/usr/local/cuda-$CUDA_VERSION --cudnn_home=/usr/local/cuda-$CUDA_VERSION --skip_tests --cmake_extra_defines 'CMAKE_CUDA_ARCHITECTURES=60;61;70;75;80' && cd /build/Release && make install DESTDIR=/build/installed"
+/bin/bash -c "/usr/bin/python3.12 /onnxruntime_src/tools/ci_build/build.py --enable_lto --build_java --build_nodejs --build_dir /build --config Release --skip_submodule_sync  --parallel --use_binskim_compliant_compile_flags --build_shared_lib --use_cuda --cuda_version=$CUDA_VERSION --cuda_home=/usr/local/cuda-$CUDA_VERSION --cudnn_home=/usr/local/cuda-$CUDA_VERSION --skip_tests --cmake_extra_defines 'CMAKE_CUDA_ARCHITECTURES=75;80;90' && cd /build/Release && make install DESTDIR=/build/installed"

tools/ci_build/github/linux/build_linux_python_package.sh

@@ -70,7 +70,7 @@ fi
 if [ "$BUILD_DEVICE" == "GPU" ]; then
     SHORT_CUDA_VERSION=$(echo $CUDA_VERSION | sed   's/\([[:digit:]]\+\.[[:digit:]]\+\)\.[[:digit:]]\+/\1/')
     #Enable CUDA and TRT EPs.
-    BUILD_ARGS+=("--use_cuda" "--use_tensorrt" "--cuda_version=$SHORT_CUDA_VERSION" "--tensorrt_home=/usr" "--cuda_home=/usr/local/cuda-$SHORT_CUDA_VERSION" "--cudnn_home=/usr/local/cuda-$SHORT_CUDA_VERSION" "--cmake_extra_defines" "CMAKE_CUDA_ARCHITECTURES=52;60;61;70;75;80")
+    BUILD_ARGS+=("--use_cuda" "--use_tensorrt" "--cuda_version=$SHORT_CUDA_VERSION" "--tensorrt_home=/usr" "--cuda_home=/usr/local/cuda-$SHORT_CUDA_VERSION" "--cudnn_home=/usr/local/cuda-$SHORT_CUDA_VERSION" "--cmake_extra_defines" "CMAKE_CUDA_ARCHITECTURES=75;80;90")
 fi
 
 if [ "$BUILD_DEVICE" == "NPU" ]; then

tools/ci_build/github/linux/build_tensorrt_c_api_package.sh

@@ -3,4 +3,4 @@ set -e -x
 mkdir -p $HOME/.onnx
 docker run --rm --volume /data/onnx:/data/onnx:ro --volume $BUILD_SOURCESDIRECTORY:/onnxruntime_src --volume $BUILD_BINARIESDIRECTORY:/build \
 --volume /data/models:/build/models:ro --volume $HOME/.onnx:/home/onnxruntimedev/.onnx -e NIGHTLY_BUILD onnxruntimecuda${CUDA_VERSION_MAJOR}xtrt86build \
-/bin/bash -c "/usr/bin/python3.12 /onnxruntime_src/tools/ci_build/build.py --build_dir /build --config Release --skip_tests --skip_submodule_sync --parallel --use_binskim_compliant_compile_flags --build_shared_lib --build_java --build_nodejs --use_tensorrt --cuda_version=$CUDA_VERSION --cuda_home=/usr/local/cuda-$CUDA_VERSION --cudnn_home=/usr --tensorrt_home=/usr --cmake_extra_defines 'CMAKE_CUDA_ARCHITECTURES=60;61;70;75;80' && cd /build/Release && make install DESTDIR=/build/installed"
+/bin/bash -c "/usr/bin/python3.12 /onnxruntime_src/tools/ci_build/build.py --build_dir /build --config Release --skip_tests --skip_submodule_sync --parallel --use_binskim_compliant_compile_flags --build_shared_lib --build_java --build_nodejs --use_tensorrt --cuda_version=$CUDA_VERSION --cuda_home=/usr/local/cuda-$CUDA_VERSION --cudnn_home=/usr --tensorrt_home=/usr --cmake_extra_defines 'CMAKE_CUDA_ARCHITECTURES=75;80;90' && cd /build/Release && make install DESTDIR=/build/installed"