Search Criteria
Package Details: python-tensorrt 10.7.0.23-1
Package Actions
Git Clone URL: | https://aur.archlinux.org/tensorrt.git (read-only, click to copy) |
---|---|
Package Base: | tensorrt |
Description: | A platform for high-performance deep learning inference on NVIDIA hardware (python bindings and tools) |
Upstream URL: | https://developer.nvidia.com/tensorrt/ |
Keywords: | ai artificial intelligence nvidia |
Licenses: | Apache-2.0, LicenseRef-custom |
Provides: | python-onnx-graphsurgeon, python-polygraphy, python-tensorflow-quantization |
Submitter: | dbermond |
Maintainer: | dbermond |
Last Packager: | dbermond |
Votes: | 20 |
Popularity: | 0.54 |
First Submitted: | 2018-07-29 16:17 (UTC) |
Last Updated: | 2024-12-07 14:13 (UTC) |
Dependencies (18)
- python (python37AUR, python311AUR, python310AUR)
- python-numpy (python-numpy-flameAUR, python-numpy-gitAUR, python-numpy1AUR, python-numpy-mkl-binAUR, python-numpy-mkl-tbbAUR, python-numpy-mklAUR)
- tensorrtAUR
- cmake (cmake-gitAUR) (make)
- cuda (cuda11.1AUR, cuda-12.2AUR, cuda12.0AUR, cuda11.4AUR, cuda11.4-versionedAUR, cuda12.0-versionedAUR) (make)
- cudnn (make)
- git (git-gitAUR, git-glAUR) (make)
- python (python37AUR, python311AUR, python310AUR) (make)
- python-build (make)
- python-installer (python-installer-gitAUR) (make)
- python-onnx (make)
- python-setuptools (make)
- python-wheel (make)
- python-onnx (optional) – for onnx_graphsurgeon python module
- python-onnxruntime (python-onnxruntime-opt, python-onnxruntime-opt-rocm, python-onnxruntime-rocm) (optional) – for onnx_graphsurgeon and polygraphy python modules
- python-protobuf (python-protobuf-gitAUR) (optional) – for polygraphy and tensorflow-quantization python modules
- python-tensorflow-cuda (python-tensorflow-cuda-gitAUR, python-tensorflow-opt-cuda) (optional) – for polygraphy python module
- python-tf2onnxAUR (optional) – for tensorflow-quantization python module
Required by (1)
Sources (13)
- 010-tensorrt-use-local-protobuf-sources.patch
- 020-tensorrt-fix-python.patch
- 030-tensorrt-onnx-tensorrt-disable-missing-source-file.patch
- cub-nvlabs
- git+https://github.com/google/benchmark.git
- git+https://github.com/NVIDIA/TensorRT.git#tag=v10.7.0
- git+https://github.com/onnx/onnx-tensorrt.git
- git+https://github.com/onnx/onnx.git
- git+https://github.com/pybind/pybind11.git
- https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/tars/TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar.gz
- https://github.com/google/protobuf/releases/download/v3.20.1/protobuf-cpp-3.20.1.tar.gz
- protobuf-protocolbuffers
- TensorRT-SLA.txt
Latest Comments
« First ‹ Previous 1 .. 3 4 5 6 7 8 9 10 Next › Last »
FuzzyAtish commented on 2022-05-15 16:40 (UTC)
@dbermond Thank you for the prompt response and resolution! Once I reinstalled that package, this one was successfully built
dbermond commented on 2022-05-15 12:05 (UTC)
@FuzzyAtish You need to rebuild python-onnx against protobuf 3.20.x, as protobuf got a soname bump. Remember that you must carefully take care of all the needed AUR rebuilds, otherwise your AUR packages becomes broken as you could see.
FuzzyAtish commented on 2022-05-15 07:52 (UTC) (edited on 2022-05-15 07:58 (UTC) by FuzzyAtish)
Hello, I'm receiving the following error when running
makepkg -si
When inspecting the current directory, I see that pkg has only 111 rights
Did anyone else come across this by any chance?
dbermond commented on 2022-02-04 21:16 (UTC)
@Draghi Package updated. Thanks for the notice and for appreciating the package.
Draghi commented on 2022-01-18 15:49 (UTC)
trtexec does not work anymore because of a missing library:
[E] [TRT] 6: [libLoader.h::DynamicLibrary::49] Error Code 6: Internal Error (Unable to load library: libnvinfer_builder_resource.so.8.2.1)
Please add it to PKGBUILD at package_tensorrt():
cp -dr --no-preserve='ownership' "TensorRT-${pkgver}/lib"/libnvinfer_builder_resource.so* "${pkgdir}/usr/lib"
Thanks for maintaining this package!
acxz commented on 2021-03-22 13:44 (UTC)
@nxxxx Take a look at the following issue: https://github.com/NVIDIA/TensorRT/issues/1064
tldr: if you want to manually install nvrtc for cuda 11.1 it works with cuda 11.2, but otherwise you need the nvrtc version provided in cuda 11.1, which means you need 11.1 for tensorrt as of now.
Homalozoa commented on 2021-03-19 07:35 (UTC)
tensorrt 7.2.3 is capable for cuda 11.2, could you remove the version constraint of cuda? thanks.
dbermond commented on 2021-02-11 15:17 (UTC)
@ilpanich As you could see, it does not build against cuda 11.2. The closed source components (downloaded from the nvidia website) strictly links to cuda 11.1 libraries and this cannot be changed, since the files are pre-compiled. So, the current source file for tensorrt 7.2.2.3 is not for cuda 11.2, but for 11.1 only. There is nothing to be fixed here, as the package is building fine. It just requires cuda11.1 from the AUR.
ilpanich commented on 2021-02-11 08:51 (UTC) (edited on 2021-02-11 08:52 (UTC) by ilpanich)
Despite NVIDIA says that the tarball is valid both for CUDA 11.1 & 11.2 ("TensorRT 7.2.2 for Linux and CUDA 11.1 & 11.2"), it seems not to build correctly with the latter. Will it be fixed?
collect2: error: ld returned 1 exit status make[2]: [parsers/onnx/CMakeFiles/getSupportedAPITest.dir/build.make:125: parsers/onnx/getSupportedAPITest] Error 1 make[1]: [CMakeFiles/Makefile2:1194: parsers/onnx/CMakeFiles/getSupportedAPITest.dir/all] Error 2
dbermond commented on 2020-10-06 18:14 (UTC)
@gsiolas cuda 11.1 broke this package. The nvidia pre-compiled binary files depends on libraries from cuda 11.0. Reverting to use only the pre-compiled files without without building the open source components (as it was made before) will not work because there would still be pre-compiled binary files linking to cuda 11.0 libraries. Workaround is to usa cuda 11.0 if you are willing to, or wait for nvidia to release a tensorrt version that supports cuda 11.1.
« First ‹ Previous 1 .. 3 4 5 6 7 8 9 10 Next › Last »