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] Support Inferentia/Neuron Runtime #1995

Open
samjo-nyang opened this issue Mar 14, 2022 · 6 comments
Open

[EKS] Support Inferentia/Neuron Runtime #1995

samjo-nyang opened this issue Mar 14, 2022 · 6 comments
Labels
area/kubernetes K8s including EKS, EKS-A, and including VMW status/icebox Things we think would be nice but are not prioritized type/enhancement New feature or request

Comments

@samjo-nyang
Copy link
Contributor

samjo-nyang commented Mar 14, 2022

What I'd like:
I think it requires the neuron driver on https://github.com/aws/aws-neuron-sdk

Any alternatives you've considered:
Nothing

@cbgbt
Copy link
Contributor

cbgbt commented Mar 14, 2022

Thanks for raising this. We're interested in integrating with Neuron, and it's something we're planning to look into down the road!

@cbgbt cbgbt added this to the backlog milestone Mar 14, 2022
@cbgbt cbgbt added type/enhancement New feature or request dependencies labels Mar 14, 2022
@cbgbt cbgbt changed the title Support Neuron Runtime on EKS [EKS] Support Inferentia/Neuron Runtime Mar 15, 2022
@cbgbt
Copy link
Contributor

cbgbt commented Mar 15, 2022

Re-titled this to be consistent with #1075, which is similar but for an ECS Inferentia variant.

@stmcginnis stmcginnis added status/needs-triage Pending triage or re-evaluation and removed priority/p2 labels Dec 1, 2022
@stmcginnis
Copy link
Contributor

Is this still needed?

@stmcginnis stmcginnis added status/needs-info Further information is requested area/kubernetes K8s including EKS, EKS-A, and including VMW and removed status/needs-triage Pending triage or re-evaluation labels Dec 19, 2022
@stmcginnis stmcginnis removed this from the backlog milestone Dec 19, 2022
@samjo-nyang
Copy link
Contributor Author

Yes, we are using more neuron instances than I created the ticket. (actively migrating workloads from gpu to neuron)

@stmcginnis stmcginnis added status/icebox Things we think would be nice but are not prioritized and removed status/needs-info Further information is requested labels Dec 20, 2022
@hustshawn
Copy link

Container SSA check-in. IHAC is running ML workloads with Inferentia on EKS. They are quite interested in Bottlerocket in terms of awesome security benefits they get with less overhead. They really want to align the company standards to use Bottlerocket for general business application as well as ML workloads. But the lack of support for Inferentia would affect their adoption.

@heichow
Copy link

heichow commented Sep 28, 2023

IHAC who is running Stable Diffusion on EKS Inf2, and they wish to adopt Bottlerocket image cache solution to reduce the large image (10+GB) pulling time from ECR around 3-4 minutes. Foreseeing the increasing GenAI model hosting with Inferentia, supporting Inferentia/Neuron runtime will have a big impact.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
area/kubernetes K8s including EKS, EKS-A, and including VMW status/icebox Things we think would be nice but are not prioritized type/enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

6 participants