Availability of TensorRT for Ubuntu 22.04 (sbsa)

Description

TensorRT (libnvinfer8, libnvinfer-dev) is not yet available at Index of /compute/cuda/repos/ubuntu2204/sbsa

Is there a timeframe by when TensorRT will be available for Ubuntu 22.04 on aarch64 (sbsa)?

Environment

TensorRT Version: 8.5.3
GPU Type: Quadro RTX 4000
Nvidia Driver Version: 520.61.05
CUDA Version: See Container
CUDNN Version: See Container
Operating System + Version: See Container
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag): Container nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04

Steps To Reproduce

docker run --rm -ti nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 bash -c 'apt update && apt install libnvinfer-dev'
==========
== CUDA ==
==========

CUDA Version 11.8.0

Container image Copyright (c) 2016-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.

WARNING: The NVIDIA Driver was not detected.  GPU functionality will not be available.
   Use the NVIDIA Container Toolkit to start this container with GPU support; see
   https://docs.nvidia.com/datacenter/cloud-native/ .

Get:1 http://ports.ubuntu.com/ubuntu-ports jammy InRelease [270 kB]
Get:2 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/sbsa  InRelease [1579 B]
Get:3 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/sbsa  Packages [151 kB]
Get:4 http://ports.ubuntu.com/ubuntu-ports jammy-updates InRelease [119 kB]
Get:5 http://ports.ubuntu.com/ubuntu-ports jammy-backports InRelease [107 kB]
Get:6 http://ports.ubuntu.com/ubuntu-ports jammy-security InRelease [110 kB]
Get:7 http://ports.ubuntu.com/ubuntu-ports jammy/restricted arm64 Packages [24.2 kB]
Get:8 http://ports.ubuntu.com/ubuntu-ports jammy/multiverse arm64 Packages [224 kB]
Get:9 http://ports.ubuntu.com/ubuntu-ports jammy/universe arm64 Packages [17.2 MB]
Get:10 http://ports.ubuntu.com/ubuntu-ports jammy/main arm64 Packages [1758 kB]
Get:11 http://ports.ubuntu.com/ubuntu-ports jammy-updates/restricted arm64 Packages [341 kB]
Get:12 http://ports.ubuntu.com/ubuntu-ports jammy-updates/universe arm64 Packages [960 kB]
Get:13 http://ports.ubuntu.com/ubuntu-ports jammy-updates/main arm64 Packages [1024 kB]
Get:14 http://ports.ubuntu.com/ubuntu-ports jammy-updates/multiverse arm64 Packages [5392 B]
Get:15 http://ports.ubuntu.com/ubuntu-ports jammy-backports/main arm64 Packages [49.0 kB]
Get:16 http://ports.ubuntu.com/ubuntu-ports jammy-backports/universe arm64 Packages [22.4 kB]
Get:17 http://ports.ubuntu.com/ubuntu-ports jammy-security/main arm64 Packages [707 kB]
Get:18 http://ports.ubuntu.com/ubuntu-ports jammy-security/multiverse arm64 Packages [1421 B]
Get:19 http://ports.ubuntu.com/ubuntu-ports jammy-security/universe arm64 Packages [732 kB]
Get:20 http://ports.ubuntu.com/ubuntu-ports jammy-security/restricted arm64 Packages [328 kB]
Fetched 24.1 MB in 2s (12.3 MB/s)                          
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
12 packages can be upgraded. Run 'apt list --upgradable' to see them.
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
E: Unable to locate package libnvinfer-dev
1 Like

Hi @b-data_it ,
Apologies for the delay,
This is on our roadmap and shall be available soon. Please stay tuned for the updates.

Thanks

1 Like

@AakankshaS Any update on this?

Incoming…

libnvinfer8_8.6.2.2-1+cuda12.0_arm64.deb and libnvinfer-dev_8.6.2.2-1+cuda12.0_arm64.deb have just been released.

@AakankshaS Two questions:

  1. Why no simultaneous release of v8.6.2 for x86_64?
  2. Does v8.6.2 equal v23.08 that was released on GitHub?

@AakankshaS Regarding v9.1.0: Will there be a deb package for both x86_64 and aarch64 (sbsa)?

TensorRT 10.0 for Ubuntu 22.04 and CUDA 12.0 to 12.4 (and CUDA 11.0 to 11.8) has been released.

Available for both x86_64 and aarch64 (sbsa). Thank you guys!