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

EKS deployment doc #17

Merged
merged 2 commits into from
Apr 22, 2022
Merged

EKS deployment doc #17

merged 2 commits into from
Apr 22, 2022

Conversation

cparisien
Copy link
Collaborator

Revised the EKS deployment doc from the main Riva docs. Restructured the flow so it's more clear, and corrected a fair number of steps based on experience deploying TBYB.

@cparisien cparisien requested a review from LynseyFabel April 20, 2022 18:47
Copy link
Contributor

@LynseyFabel LynseyFabel left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've completed my review and left some comments.

deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved

## Scale the cluster

As deployed above, the EKS cluster only provisions a single GPU node, although the given configuration permits up to 8 nodes. While a single GPU can handle a [large volume of requests](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-performance.html), the cluster can easily be scaled with more nodes.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if this is to live in the Riva User's Guide, we should change this link to a relative link.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed. Leaving this unresolved for now pending Arun's decision.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This issue is generic and we have a meeting tom with Jason to sort this out.
Merging this PR now.
Tracking this issue in https://jirasw.nvidia.com/browse/JARS-2014

deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved
deploy-eks.md Outdated Show resolved Hide resolved
@NikhilSrihari NikhilSrihari merged commit f926859 into dev/22.04 Apr 22, 2022
NikhilSrihari added a commit that referenced this pull request Apr 22, 2022
* Hindi ASR tutorial markdown (#15)

* nb to md

* fixes based on nikhil's review

* JARS-2037 and JARS-2038 (#18)

* JARS-2037 and JARS-2038

* Delete ipynb checkpoint

* Review updates

Co-authored-by: nsrihari <nsrihari@nvidia.com>

* EKS deployment doc (#17)

* EKS deployment doc

* Revisions for style consistency and review feedback

Co-authored-by: Ashish Sardana <ashishsardana21@gmail.com>
Co-authored-by: nsrihari <nsrihari@nvidia.com>
Co-authored-by: Chris Parisien <64271260+cparisien@users.noreply.github.com>
@blisc blisc deleted the eks_deployment branch February 1, 2023 16:06
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

Successfully merging this pull request may close these issues.

3 participants