Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[MXNET-703] Update onnx-tensorrt for int8/fp16 support #13906

Closed
wants to merge 3 commits into from
Closed

[MXNET-703] Update onnx-tensorrt for int8/fp16 support #13906

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
10c04bc
[MXNET-703] Update onnx-tensorrt for fp16 support
KellenSunderland Jan 16, 2019
8f990b0
Add Cuda headers to include path
KellenSunderland Jan 17, 2019
2d55cf2
Incorporate a few more bug fixes
KellenSunderland Jan 26, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion 3rdparty/onnx-tensorrt
Open in desktop
Submodule onnx-tensorrt updated 5 files
+52 −16 CMakeLists.txt
+1 −1 ShapedWeights.hpp
+39 −15 builtin_op_importers.cpp
+27 −14 onnx2trt_utils.hpp
+1 −1 third_party/onnx
1 change: 1 addition & 0 deletions ci/docker/Dockerfile.build.ubuntu_gpu_tensorrt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,3 +39,4 @@ COPY runtime_functions.sh /work/

WORKDIR /work/mxnet
ENV LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib
ENV CPLUS_INCLUDE_PATH=${CPLUS_INCLUDE_PATH}:/usr/local/cuda-10.0/targets/x86_64-linux/include/