saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-06 00:03:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[TensorRT EP] make --use_tensorrt_builtin_parser the default behavior in build.py (#15320)

Browse source 
Change the default behavior to link against the nvonnxparser library
(onnx-tensorrt parser) that is included with the TensorRT package.
Previously, the default behavior was to build and statically link
against the OSS onnx-tensorrt parser.
Historically, we wanted to incorporate the latest commits/fixes from OSS
parser.
These days the OSS parser is not significantly different from the
included parser library so there is less reason to build against it by
default.
By linking with parser shared library from TensorRT library, the major
benefit is it's much easier to
build/link against a minor version update of TensorRT. And OnnxRuntime
can be updated with a new TensorRT minor version by simply replacing
TensorRT libraries with the newer version. (because the parser is no
longer statically linked into onnxruntime)

Added --use_tensorrt_oss_parser to build.py to support the previous
default behavior. (build + static link OSS parser)
This commit is contained in:
George Wu 2023-04-05 07:53:29 -07:00 committed by GitHub
parent fe0db63dee
commit 4db10c93d1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 9 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
cmake/onnxruntime_providers.cmake
View file

@ -696,7 +696,9 @@ if (onnxruntime_USE_TENSORRT)
endif()
include_directories(${TENSORRT_INCLUDE_DIR})
# ${TENSORRT_LIBRARY} is empty if we link nvonnxparser_static.
# nvonnxparser_static is linked against tensorrt libraries in onnx-tensorrt
# See https://github.com/onnx/onnx-tensorrt/blob/8af13d1b106f58df1e98945a5e7c851ddb5f0791/CMakeLists.txt#L121
set(trt_link_libs cudnn cublas ${CMAKE_DL_LIBS} ${TENSORRT_LIBRARY})
file(GLOB_RECURSE onnxruntime_providers_tensorrt_cc_srcs CONFIGURE_DEPENDS

8
tools/ci_build/build.py
View file

@ -499,7 +499,10 @@ def parse_arguments():
"--use_tvm_hash", action="store_true", help="Build ipp-crypto for hash generation. It is used by TVM EP only"
)
parser.add_argument("--use_tensorrt", action="store_true", help="Build with TensorRT")
parser.add_argument("--use_tensorrt_builtin_parser", action="store_true", help="Use TensorRT builtin parser")
parser.add_argument(
"--use_tensorrt_builtin_parser", action="store_true", default=True, help="Use TensorRT builtin parser"
)
parser.add_argument("--use_tensorrt_oss_parser", action="store_true", help="Use TensorRT OSS parser")
parser.add_argument(
"--tensorrt_placeholder_builder", action="store_true", help="Instantiate Placeholder TensorRT Builder"
)
@ -916,7 +919,8 @@ def generate_build_tree(
"-Donnxruntime_USE_TENSORRT=" + ("ON" if args.use_tensorrt else "OFF"),
"-Donnxruntime_SKIP_AND_PERFORM_FILTERED_TENSORRT_TESTS="
+ ("ON" if not args.tensorrt_placeholder_builder else "OFF"),
"-Donnxruntime_USE_TENSORRT_BUILTIN_PARSER=" + ("ON" if args.use_tensorrt_builtin_parser else "OFF"),
"-Donnxruntime_USE_TENSORRT_BUILTIN_PARSER="
+ ("ON" if args.use_tensorrt_builtin_parser and not args.use_tensorrt_oss_parser else "OFF"),
"-Donnxruntime_TENSORRT_PLACEHOLDER_BUILDER=" + ("ON" if args.tensorrt_placeholder_builder else "OFF"),
# set vars for TVM
"-Donnxruntime_USE_TVM=" + ("ON" if args.use_tvm else "OFF"),