Drastic reduction in trt plan cache size

Compiling.md

@@ -32,7 +32,7 @@ As also mentioned in the instructions below but repeated here for visibility, if
       * Some version of g++ that supports at least C++14.
       * If using the OpenCL backend, a modern GPU that supports OpenCL 1.2 or greater, or else something like [this](https://software.intel.com/en-us/opencl-sdk) for CPU. But if using CPU, Eigen should be better.
       * If using the CUDA backend, CUDA 11 or later and a compatible version of CUDNN based on your CUDA version (https://developer.nvidia.com/cuda-toolkit) (https://developer.nvidia.com/cudnn) and a GPU capable of supporting them.
-      * If using the TensorRT backend, in addition to a compatible CUDA Toolkit (https://developer.nvidia.com/cuda-toolkit), you also need TensorRT (https://developer.nvidia.com/tensorrt) that is at least version 8.5.
+      * If using the TensorRT backend, in addition to a compatible CUDA Toolkit (https://developer.nvidia.com/cuda-toolkit), you also need TensorRT (https://developer.nvidia.com/tensorrt) that is at least version 10.0.
       * If using the Eigen backend, Eigen3. With Debian packages, (i.e. apt or apt-get), this should be `libeigen3-dev`.
       * zlib, libzip. With Debian packages (i.e. apt or apt-get), these should be `zlib1g-dev`, `libzip-dev`.
       * If you want to do self-play training and research, probably Google perftools `libgoogle-perftools-dev` for TCMalloc or some other better malloc implementation. For unknown reasons, the allocation pattern in self-play with large numbers of threads and parallel games causes a lot of memory fragmentation under glibc malloc that will eventually run your machine out of memory, but better mallocs handle it fine.
@@ -62,7 +62,7 @@ As also mentioned in the instructions below but repeated here for visibility, if
       * Microsoft Visual Studio for C++. Version 15 (2017) has been tested and should work, other versions might work as well.
       * If using the OpenCL backend, a modern GPU that supports OpenCL 1.2 or greater, or else something like [this](https://software.intel.com/en-us/opencl-sdk) for CPU. But if using CPU, Eigen should be better.
       * If using the CUDA backend, CUDA 11 or later and a compatible version of CUDNN based on your CUDA version (https://developer.nvidia.com/cuda-toolkit) (https://developer.nvidia.com/cudnn) and a GPU capable of supporting them. I'm unsure how version compatibility works with CUDA, there's a good chance that later versions than these work just as well, but they have not been tested.
-      * If using the TensorRT backend, in addition to a compatible CUDA Toolkit (https://developer.nvidia.com/cuda-toolkit), you also need TensorRT (https://developer.nvidia.com/tensorrt) that is at least version 8.5.
+      * If using the TensorRT backend, in addition to a compatible CUDA Toolkit (https://developer.nvidia.com/cuda-toolkit), you also need TensorRT (https://developer.nvidia.com/tensorrt) that is at least version 10.0.
       * If using the Eigen backend, Eigen3, version 3.3.x. (http://eigen.tuxfamily.org/index.php?title=Main_Page#Download).
       * zlib. The following package might work, https://www.nuget.org/packages/zlib-vc140-static-64/, or alternatively you can build it yourself via something like: https://github.com/kiyolee/zlib-win-build
       * libzip (optional, needed only for self-play training) - for example https://github.com/kiyolee/libzip-win-build

cpp/CMakeLists.txt

@@ -300,7 +300,7 @@ elseif(USE_BACKEND STREQUAL "TENSORRT")
     message(FATAL_ERROR "${ColorBoldRed} NvInfer.h was NOT found, specify TENSORRT_INCLUDE_DIR to indicate where it is. ${ColorReset}")
   endif()
   find_library(TENSORRT_LIBRARY nvinfer HINTS ${TENSORRT_ROOT_DIR} PATH_SUFFIXES lib)
-  file(READ "${TENSORRT_INCLUDE_DIR}/NvInferVersion.h" tensorrt_version_header)
+  file(STRINGS "${TENSORRT_INCLUDE_DIR}/NvInferVersion.h" tensorrt_version_header NEWLINE_CONSUME)
   string(REGEX MATCH "#define NV_TENSORRT_MAJOR ([0-9]+)" tensorrt_version_macro ${tensorrt_version_header})
   set(TENSORRT_VERSION_MAJOR ${CMAKE_MATCH_1})
   string(REGEX MATCH "#define NV_TENSORRT_MINOR ([0-9]+)" tensorrt_version_macro ${tensorrt_version_header})
@@ -311,9 +311,10 @@ elseif(USE_BACKEND STREQUAL "TENSORRT")
   # Version 8 is required for serializing the builder timing cache.
   # Version 8.2 is required for eliminating the global logger for Builder and Runtime.
   # Version 8.5 is required for eliminating many deprecated APIs and adopting new features.
-  # Version 8.6 is for CUDA 12 support and further reduction in initialization time.
-  if(TENSORRT_VERSION VERSION_LESS 8.5)
-    message(FATAL_ERROR "TensorRT 8.5 or greater is required but ${TENSORRT_VERSION} was found.")
+  # Version 8.6 is required for CUDA 12 support and further reduction in initialization time.
+  # Version 10.0 is required for better CUDA 12 support and drastic reduction in plan cache size.
+  if(TENSORRT_VERSION VERSION_LESS 10.0)
+    message(FATAL_ERROR "TensorRT 10.0 or greater is required but ${TENSORRT_VERSION} was found.")
   endif()
   include_directories(SYSTEM ${CUDAToolkit_INCLUDE_DIRS} ${TENSORRT_INCLUDE_DIR}) #SYSTEM is for suppressing some compiler warnings in thrust libraries
   target_link_libraries(katago CUDA::cudart_static ${TENSORRT_LIBRARY})