Cannot build r22.03 onnxruntime_backend with tensorrt

[ZJU-lishuang]

Description I was unable to build the onnxruntime_backend with OpenVino for Triton Inference Server r22.03 using compatible ONNXRuntime and tensorrt versions (from Triton Inference Server compatibility matrix).

Triton Information r22.03

To Reproduce follow the readme in onnxruntime_backend

cmake \
-DCMAKE_INSTALL_PREFIX:PATH=`pwd`/install \
-DTRITON_BUILD_CUDNN_HOME='/usr/lib/x86_64-linux-gnu/' \
-DTRITON_BUILD_ONNXRUNTIME_VERSION=1.10.0 -DTRITON_BUILD_CONTAINER_VERSION=22.03 -DTRITON_ENABLE_ONNXRUNTIME_TENSORRT=ON \
-DTRITON_BACKEND_REPO_TAG=r22.03 -DTRITON_CORE_REPO_TAG=r22.03 -DTRITON_COMMON_REPO_TAG=r22.03 ..

And will see the error. /usr/include/x86_64-linux-gnu/NvInferRuntimeCommon.h:56:10: fatal error: cuda_runtime_api.h: No such file or directory

Expected behavior ONNX Backend Should build and run without issues.

[ZJU-lishuang]

-- 
-- ******** Summary ********
--   CMake version             : 3.21.0
--   CMake command             : /workspace/cmake-3.21.0-linux-x86_64/bin/cmake
--   System                    : Linux
--   C++ compiler              : /usr/bin/c++
--   C++ compiler version      : 9.4.0
--   CXX flags                 :  -ffunction-sections -fdata-sections -DCPUINFO_SUPPORTED -Wnon-virtual-dtor
--   Build type                : Release
--   Compile definitions       : EIGEN_MPL2_ONLY;PLATFORM_POSIX;__STDC_FORMAT_MACROS
--   CMAKE_PREFIX_PATH         : 
--   CMAKE_INSTALL_PREFIX      : /usr/local
--   CMAKE_MODULE_PATH         : /workspace/onnxruntime/cmake/external
-- 
--   ONNX version              : 1.10.1
--   ONNX NAMESPACE            : onnx
--   ONNX_USE_LITE_PROTO       : OFF
--   USE_PROTOBUF_SHARED_LIBS  : OFF
--   Protobuf_USE_STATIC_LIBS  : ON
--   ONNX_DISABLE_EXCEPTIONS   : OFF
--   ONNX_WERROR               : OFF
--   ONNX_BUILD_TESTS          : OFF
--   ONNX_BUILD_BENCHMARKS     : OFF
--   ONNXIFI_DUMMY_BACKEND     : OFF
--   ONNXIFI_ENABLE_EXT        : OFF
-- 
--   Protobuf compiler         : 
--   Protobuf includes         : 
--   Protobuf libraries        : 
--   BUILD_ONNX_PYTHON         : OFF
-- Looking for strtof_l
-- Looking for strtof_l - found
-- Looking for strtoull_l
-- Looking for strtoull_l - found
-- The CUDA compiler identification is NVIDIA 11.6.112
-- Detecting CUDA compiler ABI info
-- Detecting CUDA compiler ABI info - done
-- Check for working CUDA compiler: /usr/local/cuda/bin/nvcc - skipped
-- Detecting CUDA compile features
-- Detecting CUDA compile features - done
-- CMAKE_CUDA_COMPILER_VERSION: 11.6.112
-- Looking for clock_gettime in rt
-- Looking for clock_gettime in rt - found
-- Found TensorRT headers at /usr/include/x86_64-linux-gnu
-- Find TensorRT libs at /usr/lib/x86_64-linux-gnu/libnvinfer.so;/usr/lib/x86_64-linux-gnu/libnvinfer_plugin.so
-- Found TENSORRT: /usr/include/x86_64-linux-gnu  
-- The ASM compiler identification is GNU
-- Found assembler: /usr/bin/cc
-- Configuring done
-- Generating done

[ZJU-lishuang]

onnxruntime