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

Fix TRTIS_ENABLE_GPU=OFF builds #568

Merged
merged 1 commit into from
Aug 20, 2019

Conversation

dougn
Copy link
Contributor

@dougn dougn commented Aug 20, 2019

  • fix #ifdef TRTIS_ENABLE_GPU logic in backend_context.cc

Discovered this while working on build automation. Very simple fix for the build.

* fix #ifdef TRTIS_ENABLE_GPU logic in backend_context.cc
@deadeyegoodwin deadeyegoodwin merged commit 2cc2162 into triton-inference-server:master Aug 20, 2019
@deadeyegoodwin
Copy link
Contributor

@dougn Thanks for the fix!

@dougn
Copy link
Contributor Author

dougn commented Aug 24, 2019

Looks like this was reintroduced in another pull request merge from a non-up-to-date branch

https://github.com/NVIDIA/tensorrt-inference-server/blob/master/src/core/ensemble_scheduler.cc#L660 has an extra ')'

@GuanLuo
Copy link
Contributor

GuanLuo commented Aug 26, 2019

@dougn You are right, and it will be fixed as part of #582

@deadeyegoodwin
Copy link
Contributor

@dougn We are adding some test automation to detect this kind of error to avoid this problem in the future.

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

Successfully merging this pull request may close these issues.

3 participants