Skip to content
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

Core dump when call getDeviceMemorySizeForProfileV2 #4302

Open
tp-nan opened this issue Dec 26, 2024 · 4 comments
Open

Core dump when call getDeviceMemorySizeForProfileV2 #4302

tp-nan opened this issue Dec 26, 2024 · 4 comments

Comments

@tp-nan
Copy link

tp-nan commented Dec 26, 2024

Description

Core dumped when call getDeviceMemorySizeForProfileV2. When use getDeviceMemorySizeForProfile, all work well.

Environment

TensorRT Version: 10.7

NVIDIA GPU: 3080TI

NVIDIA Driver Version: 530.41.03

CUDA Version: 11.8 in docker / 12.1 for system

Steps To Reproduce

Is a resnet18, with two profiles(1->4)

@lix19937
Copy link

Do you set BuilderFlag::kWEIGHT_STREAMING during engine building

@tp-nan
Copy link
Author

tp-nan commented Jan 6, 2025

Do you set BuilderFlag::kWEIGHT_STREAMING during engine building

No

@lix19937
Copy link

lix19937 commented Jan 6, 2025

So you need add.

@tp-nan
Copy link
Author

tp-nan commented Jan 6, 2025

So you need add.

Thank you for the information. If designed this way, I would suggest to add relevant documentation. As WEIGHT STREAMING requires strongly-typed models, many models cannot be used.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants