-
Notifications
You must be signed in to change notification settings - Fork 2.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
TensorRT 10.7 when generating engine on GPU 5090 laptop #4317
Comments
Maybe you have to use last cuda or incoming cuda 12.7 |
--update |
From https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html#compute-capability-platform and https://docs.nvidia.com/deeplearning/tensorrt-cloud/latest/support-compatibility.html, rtx5090 as GeForce gpu as Blackwell arch, current trt version not support it. I think will support soon. |
So will next TensorRT version support 50XX Series (blackwell,12.0)? Will it be released this month? |
@johnnynunez At current time 2025-01-14, the latest cuda version is 12.6. |
@kevinch-nv FYI, make sure ? |
@lix19937 new cuda 12.7 and drivers are coming for enable binares for build with all libraries |
I think it will not released this month. |
Description
Hi, I'm trying to use tensorrt 10.7 to generate engine on Nvidia 5090 laptop. The process failed and I'm not sure if 50XX series are currently not supported. Thank you.
Environment
TensorRT Version: 10.7
NVIDIA GPU: 5090 Laptop
NVIDIA Driver Version: 546.1
CUDA Version: 12.6
The text was updated successfully, but these errors were encountered: