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

Add support for Oracle Cloud in deploy #6850

Merged
merged 10 commits into from
Feb 9, 2024

Conversation

bruno-garbaccio
Copy link
Contributor

Following issue #6849,, here is a proposal to have Triton server working on the OKE service of Oracle Cloud.

The directory deploy/oci is based on deploy/aws with some minor adjustments to have it run on Oracle Cloud.

@rmccorm4
Copy link
Collaborator

rmccorm4 commented Feb 2, 2024

Hi @bruno-garbaccio, thanks for submitting this PR. Have you submitted a CLA as described here: https://github.com/triton-inference-server/server/blob/main/CONTRIBUTING.md#contributor-license-agreement-cla?

@bruno-garbaccio
Copy link
Contributor Author

Hi @rmccorm4 , thanks for your answer. I just submitted it, I didn't see this requirement, thanks for the heads-up.

@rmccorm4
Copy link
Collaborator

rmccorm4 commented Feb 2, 2024

Thanks! CC @nealvaidya @mengdong @nv-kmcgill53 @whoisj could you give this a look over when you get a chance?

@bruno-garbaccio
Copy link
Contributor Author

Hi @rmccorm4, @nealvaidya , @mengdong , @nv-kmcgill53 @whoisj I know you guys are busy with a ton of things but do you think this could be reviewed this week? I would like to have a communication in one of our Oracle Blogs about the support of OCI for the deployment and we have a deadline for this if we want it to happen during GTC. I run the tests in my OCI tenant,took the "aws" repo as a basis and try to respect the README.md format that was set for "aws". Do not hesitate to reach out for questions!

@mengdong
Copy link
Contributor

mengdong commented Feb 6, 2024

the helm chart and instruction looks good to me!

@bruno-garbaccio
Copy link
Contributor Author

bruno-garbaccio commented Feb 8, 2024

Hi, I saw the pre-commit run failed at line 160 in the readme, at the level of the url: s3://https://<OCI_NAMESPACE>.compat.objectstorage.<OCI_REGION>.oraclecloud.com:443/triton-inference-server-repository

This url comes from the documentation https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/user_guide/model_repository.html and in the OCI case there are some placeholders to fill. I don't have a full error log. @rmccorm4 , can you tell me if there's anything I could do?

deploy/oci/README.md Outdated Show resolved Hide resolved
deploy/oci/README.md Outdated Show resolved Hide resolved
@rmccorm4
Copy link
Collaborator

rmccorm4 commented Feb 9, 2024

Hi @bruno-garbaccio, I believe pre-commit is just failing for trailing whitespace - I added some suggestions above to fix it. Otherwise, LGTM and I can approve/merge.

rmccorm4 and others added 3 commits February 9, 2024 12:06
Co-authored-by: Ryan McCormick <mccormick.codes@gmail.com>
Co-authored-by: Ryan McCormick <mccormick.codes@gmail.com>
@rmccorm4
Copy link
Collaborator

rmccorm4 commented Feb 9, 2024

Dong, J, and Neal all gave their seal of approval, so merging.

@rmccorm4 rmccorm4 merged commit 3dfb7b1 into triton-inference-server:main Feb 9, 2024
3 checks passed
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