mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-15 20:50:42 +00:00
e8b0ae8923
* updated cmake files for trt * added trt execution provider * added trt basic test * removed trt_path action attribute * Add files via upload * Update build.py * Update trt_allocator.h * fixed issues found by reviewers * changed cast operator * added comment for custom kernel implementation * changed auto to auto& * changed to function compile APIs for TRT execution provider * changed to function compile APIs for TRT execution provider * added new DType DInt64 * adapted to the changes of onnxruntime_c_api * removed trt kernel (use function compile instead) * updated onnx-tensorrt submodule * set default memory type to TRT fused kernel * resolve merge conflict * fixed the issue that USE_CUDA conflicts with USE_TRT * construct graph by adding nodes in topological order * made changes for Windows * change buffers type * bypass HasImplementationOf check for TRT XP because TRT kernel is not registered * added domain to version info in rebuilt model proto * added trt to test option list * added DomainToVersionMap() to GraphViewer * removed Copy() * fixed broken code * format the code to clang format * used local reference to the frequently used values * fixed a couple of issues according to reviewers feedback * fixed a couple of issues according to reviewers feedback * added python binding for TRT and enable use_cuda when use_trt is on * fixed a redefinition issue * changed shared_ptr to unique_ptr on trt engines, and made a few changes required by reviewers * enabled trtexecution provider for unit tests * renamed trt to tensorrt * added tesorrt to python binding * update submodule onnx and onnx-tensorrt * made a couple of minor changes based on reviewer's feedback * added CUDA_CHECK * removed test code * fixed broken code after merge * updated onnx-tensorrt submodule * added post processing to align trt inputs/outputs with graph inputs/outputs * updated onnx submodule * added CUDA fallback for TensorRT and fixed TensorRT cmake issue * added ci pipeline for tensorrt and removed some redundent code from trt xp * fixed syntax issue * updated onnx-tensorrt submodule * fix trt build problem by: (#602) 1. Add additional /wd for debug build 2. Add io.h for additional targets 3. Bring back mb version of getopt * Update install_ubuntu.sh * Update linux-gpu-tensorrt-ci-pipeline.yml * Update linux-gpu-tensorrt-ci-pipeline.yml * Update run_build.sh * Update run_build.sh * Update run_build.sh * Update run_build.sh * fixed the issue that GetKernelRegistry returns nullptr * merged master to this branch * moved some data types to private * fixed tensorrt CI pipeline issue * customized test data for TensorRT pipeline * added onnx-tensorrt in json file and fixed an issue in ci script * added comments
46 lines
1.7 KiB
Text
46 lines
1.7 KiB
Text
# Tag: nvcr.io/nvidia/tensorrt:19.02-py3
|
|
# Label: com.nvidia.cuda.version: 10.0.130
|
|
# Label: com.nvidia.cudnn.version: 7.4.2
|
|
# Ubuntu 16.04
|
|
FROM nvcr.io/nvidia/tensorrt:19.02-py3
|
|
|
|
ARG PYTHON_VERSION=3.5
|
|
|
|
ADD scripts /tmp/scripts
|
|
ENV PATH="/opt/cmake/bin:${PATH}"
|
|
RUN /tmp/scripts/install_ubuntu.sh -p ${PYTHON_VERSION} && /tmp/scripts/install_deps.sh && rm -rf /tmp/scripts
|
|
|
|
WORKDIR /root
|
|
|
|
# Allow configure to pick up GDK and CuDNN where it expects it.
|
|
# (Note: $CUDNN_VERSION is defined by NVidia's base image)
|
|
RUN _CUDNN_VERSION=$(echo $CUDNN_VERSION | cut -d. -f1-2) && \
|
|
mkdir -p /usr/local/cudnn-$_CUDNN_VERSION/cuda/include && \
|
|
ln -s /usr/include/cudnn.h /usr/local/cudnn-$_CUDNN_VERSION/cuda/include/cudnn.h && \
|
|
mkdir -p /usr/local/cudnn-$_CUDNN_VERSION/cuda/lib64 && \
|
|
ln -s /etc/alternatives/libcudnn_so /usr/local/cudnn-$_CUDNN_VERSION/cuda/lib64/libcudnn.so && \
|
|
ln -s /usr/local/cudnn{-$_CUDNN_VERSION,}
|
|
|
|
# Build and Install LLVM
|
|
ARG LLVM_VERSION=6.0.1
|
|
RUN cd /tmp && \
|
|
wget --no-verbose http://releases.llvm.org/$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz && \
|
|
xz -d llvm-$LLVM_VERSION.src.tar.xz && \
|
|
tar xvf llvm-$LLVM_VERSION.src.tar && \
|
|
cd llvm-$LLVM_VERSION.src && \
|
|
mkdir -p build && \
|
|
cd build && \
|
|
cmake .. -DCMAKE_BUILD_TYPE=Release && \
|
|
cmake --build . -- -j$(nproc) && \
|
|
cmake -DCMAKE_INSTALL_PREFIX=/usr/local/llvm-$LLVM_VERSION -DBUILD_TYPE=Release -P cmake_install.cmake && \
|
|
cd /tmp && \
|
|
rm -rf llvm*
|
|
|
|
ENV LD_LIBRARY_PATH /usr/local/openblas/lib:$LD_LIBRARY_PATH
|
|
|
|
ARG BUILD_USER=onnxruntimedev
|
|
ARG BUILD_UID=1000
|
|
WORKDIR /home/$BUILD_USER
|
|
RUN adduser --gecos 'onnxruntime Build User' --disabled-password $BUILD_USER --uid $BUILD_UID
|
|
USER $BUILD_USER
|
|
|