Yifan Li 7be1d4aad3 [TensorRT EP] Update TRT10.0 deprecated api (#20989) ... ### Description <!-- Describe your changes. --> Note: * This PR would remove C4996 suppression in tensorrt_execution_provider.cc only (according to Nvidia, places with nvinfer.h included need C4996 suppression, when /Zc:__cplusplus is enabled in ORT win build) * A follow-up PR will be raised to update deprecated TRT Plugin api usage. Here are deprecated apis to be updated in this PR: | deprecated api | Update | | ------------------------------------------------------------ | ------------------------------------------------------------ | | [kCUBLAS](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/namespacenvinfer1.html#a9e1d81e5a8bfeb38b86e22a66d5f836a) | / | | [kCUBLAS_LT](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/namespacenvinfer1.html#a9e1d81e5a8bfeb38b86e22a66d5f836a) | / | | [kCUDNN](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/namespacenvinfer1.html#a9e1d81e5a8bfeb38b86e22a66d5f836a) | / | | [reallocateOutput](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1v__1__0_1_1_i_output_allocator.html#acae6441d4029584cc1c6550917518691) | Superseded by [reallocateOutputAsync](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1v__1__0_1_1_i_output_allocator.html#aa40eeb891c1dfe4c1bbf1eabe8c705ab) with cudaStream_t argument | | [createExecutionContextWithoutDeviceMemory](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1_i_cuda_engine.html#adc86bcc42b098204997396ef2b1093fb) | Superseded by [createExecutionContext()](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1_i_cuda_engine.html#a35de29aa6134165a5b14a537e6d99e82) with parameter.<br />Check [ExecutionContextAllocationStrategy::kUSER_MANAGED](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/namespacenvinfer1.html#ac6251a050df629edfc0ce037fa366503) for more detail | ### 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. --> TRT deprecated api list: https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/deprecated.html		2024-07-01 22:55:20 -07:00
..
codegen	Replace some ORT_ENFORCE with ORT_THROW_IF_ERROR (#18812)	2023-12-14 10:14:22 -08:00
common	Update comment in cpuid_info.cc (#20974)	2024-06-10 08:52:38 -05:00
dll
dlpack
eager
flatbuffers	Use flatbuffers::String::str instead of c_str. (#20487)	2024-04-27 13:41:38 +10:00
framework	Initial PR for VSINPU execution provider (#20903)	2024-06-28 21:48:34 -07:00
graph	Update the functions in tensorprotoutils.h to use std::filesystem::path instead (#20920)	2024-06-28 20:03:57 -07:00
mickey	Adding a sm80 q4 gemm kernel for small tiles (#20545)	2024-06-12 16:02:26 -07:00
mlas	[MLAS] add q4 quantize and transpose kernel to support MatMulNBits QDQ fuse (#21054)	2024-06-19 17:15:45 -07:00
optimizer	Update the functions in tensorprotoutils.h to use std::filesystem::path instead (#20920)	2024-06-28 20:03:57 -07:00
platform	Fix Crash When Enabling and Disabling ETW with Old Callbacks (#21086)	2024-06-20 06:45:45 -07:00
providers	[TensorRT EP] Update TRT10.0 deprecated api (#20989)	2024-07-01 22:55:20 -07:00
quantization
session	Update the functions in tensorprotoutils.h to use std::filesystem::path instead (#20920)	2024-06-28 20:03:57 -07:00
util	[MLAS] add q4 quantize and transpose kernel to support MatMulNBits QDQ fuse (#21054)	2024-06-19 17:15:45 -07:00