Package Details: tensorrt 10.16.0.72-1

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
Upstream URL: https://developer.nvidia.com/tensorrt/
Keywords: ai artificial intelligence nvidia
Licenses: Apache-2.0 AND LicenseRef-TensorRT-LICENSE-AGREEMENT
Submitter: dbermond
Maintainer: dbermond
Last Packager: dbermond
Votes: 21
Popularity: 0.039334
First Submitted: 2018-07-29 16:17 (UTC)
Last Updated: 2026-03-27 15:16 (UTC)

Dependencies (20)

Sources (11)

Latest Comments

« First ‹ Previous 1 2 3 4 5 6 7 .. 13 Next › Last »

medaminezghal commented on 2025-12-20 10:28 (UTC)

@dbermond This update has broke the TensorRT URL by removing the CPU arch from it.

dbermond commented on 2025-12-19 18:43 (UTC)

@medaminezghal In TensorRt-RTX repository, there is only demos and samples, so I see no need to provide a package for this. Regarding the suggestion about "tests", sorry, but I'm not willing to add such type of testing procedure (just import a python module), as this is non-standard in python packages. A proper upstream python testing system should be used for testing python software. The onnx git submodules were updated, thanks for reporting.

medaminezghal commented on 2025-12-17 15:18 (UTC) (edited on 2025-12-17 15:18 (UTC) by medaminezghal)

@dbermond Also benchmark isn't necessary anymore as it's remove from onnx from version 1.17.0 and the used version from onnx-tensorrt is 1.18.0.

medaminezghal commented on 2025-12-17 15:00 (UTC)

@dbermond Also if you can add those tests from the TensorRT documentation:

python3
>>> import tensorrt
>>> print(tensorrt.__version__)
>>> assert tensorrt.Builder(tensorrt.Logger())

python3
>>> import tensorrt_lean as trt
>>> print(trt.__version__)
>>> assert trt.Runtime(trt.Logger())

python3
>>> import tensorrt_dispatch as trt
>>> print(trt.__version__)
>>> assert trt.Runtime(trt.Logger())

This will help ensure that the build works fine.

medaminezghal commented on 2025-12-17 14:48 (UTC)

@dbermond I mean providing this package that already include its python package.

dbermond commented on 2025-12-15 04:04 (UTC)

@medaminezghal implemented the 'tensorrt_dispatch' and 'tensorrt_lean' python modules built from the open source software repository. As far as I could gather, 'tensorrt_rtx' python module is for Windows only, and it does not build for me. You can verify that 'tensorrt_rtx' python module is not available in the downloaded GNU/Linux source file, but only 'tensorrt', 'tensorrt_dispatch' and 'tensorrt_lean'.

medaminezghal commented on 2025-12-09 15:01 (UTC)

@dbermond I think you need to install tensorrt_dispatch, tensorrt_lean and tensorrt instead of the packages that exist under tools because they don't have the same versions as TensorRT. Also Could you provide TensorRt_RTX?

idanka commented on 2025-10-16 23:29 (UTC)

@dbermond Sry Manjaro is up to date, but latest cuda package 12.9.1-2 is installed.

dbermond commented on 2025-10-14 20:42 (UTC)

@idanka I have just checked, and the package is building perfectly fine in an up-to-date Arch Linux system with cuda 13.0.2. The compute_110 architecture is supported by cuda 13, and I cannot reproduce your issue. Make sure that you have an up-to-date Arch Linux system with the latest packaged cuda version installed. The hardware is not relevant at build time, but only at run time, and you can build it even in a system without a nvidia gpu.

idanka commented on 2025-10-14 20:22 (UTC) (edited on 2025-10-14 20:24 (UTC) by idanka)

Update error nvidia rtx 3050

nvcc fatal   : Unsupported gpu architecture 'compute_110'
make[1]: *** [CMakeFiles/cmTC_10e2b.dir/build.make:82: CMakeFiles/cmTC_10e2b.dir/main.cu.o] Error 1
make[1]: Leaving directory '/var/tmp/pamac-build-dankahazi/tensorrt/src/build/CMakeFiles/CMakeScratch/TryCompile-uJWGun'
make: *** [Makefile:134: cmTC_10e2b/fast] Error 2

CMake will not be able to correctly generate this project. Call Stack (most recent call first): CMakeLists.txt:102 (project)

-- Configuring incomplete, errors occurred! ==> HIBA: Hiba történt a build()-ben. Megszakítás...

« First ‹ Previous 1 2 3 4 5 6 7 .. 13 Next › Last »