Hey!
I am currently working on a project, but I am not sure of its feasibility.
I need to run Deepstream 6.2 on my RTX 2080.
The quickstart guide gives some info.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html
It says that Deepstream runs on NVIDIA Ampere architectures, but Turing is not mentioned.
However, the RTX 2080 is mentioned on the page, and on some other pages.
So is my RTX 2080 really compatible?
Thanks
RTX2080 is supported.
Thanks.
So is it an oversight in the quickstart guide?
If it’s not written in the doc, there may be a good reason.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
The mainstream GPU architectures are supported, but we cannot verify all different variants, thus only listed a number of supported GPUs. Besides the GPU architecture, the driver version is the most important factor as the libraries on top depend on it. Also, the GPU memory size should be considered as it impacts the model or service used in your pipelines.
This document uses the term dGPU (“discrete GPU”) to refer to NVIDIA GPU expansion card products such as NVIDIA Tesla® T4 , NVIDIA GeForce® GTX 1080, NVIDIA GeForce® RTX 2080 and NVIDIA GeForce® RTX 3080. This version of DeepStream SDK runs on specific dGPU products on x86_64 platforms supported by NVIDIA driver 525.85.12 and NVIDIA TensorRT™ 8.5.2.2 and later versions.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.