Skip to content

[Feature][KubeAI] Providing resource profiles for Gaudi and Xeon #1075

@joshuayao

Description

@joshuayao

Priority

Undecided

OS type

Ubuntu

Hardware type

Xeon-GNR

Running nodes

Single Node

Description

A resource profile of KubeAI maps a type of compute resource (i.e. Gaudi, Xeon) to a collection of Kubernetes settings that are configured on inference server Pods. Each model specifies the resource profile that it requires.

Metadata

Metadata

Assignees

Labels

Backlogfeatures in backlogfeatureNew feature or request

Projects

Status

Done

Relationships

None yet

Development

No branches or pull requests

Issue actions