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.

Sign up for GitHub

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

Jump to bottom

Why the time cost of inferring resnet50-v2-7 with tvm-cuda much smallar than using tensorrt on x86? #15276

Closed
Dsqds opened this issue Jul 10, 2023 · 1 comment
Closed

Why the time cost of inferring resnet50-v2-7 with tvm-cuda much smallar than using tensorrt on x86? #15276

Dsqds opened this issue Jul 10, 2023 · 1 comment
Labels
needs-triage PRs or issues that need to be investigated by maintainers to find the right assignees to address it type: bug

Comments

@Dsqds
Copy link

Dsqds commented Jul 10, 2023 •
edited
Loading

It cost 0.11ms when I inferred resnet50-v2-7 with tvm-cuda on x86.
Then I used the tensorrt to infer the same model with fp16, it cost 0.4ms .
Is it normal that tvm-cuda so much faster than tensorrt on x86?
@Dsqds Dsqds added needs-triage PRs or issues that need to be investigated by maintainers to find the right assignees to address it type: bug labels Jul 10, 2023
@Dsqds Dsqds changed the title Why the time cost of inferring resnet50-v2-7 with tvm-cuda smallar than using tensorrt on x86? Why the time cost of inferring resnet50-v2-7 with tvm-cuda much smallar than using tensorrt on x86? Jul 10, 2023
@masahi
Copy link
Member

masahi commented Jul 10, 2023

Please use https://discuss.tvm.apache.org/

@masahi masahi closed this as completed Jul 10, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
needs-triage PRs or issues that need to be investigated by maintainers to find the right assignees to address it type: bug
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@masahi @Dsqds