-
Notifications
You must be signed in to change notification settings - Fork 34
Support computedomain for multi-node NIMServices #712
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
base: main
Are you sure you want to change the base?
Conversation
varunrsekar
commented
Nov 6, 2025
- TODO: Resolve NVIDIA/k8s-dra-driver-gpu dependency
- TODO: Resolve kserve not supporting k8s.io/* dependency version > v1.33
Signed-off-by: Varun Ramachandra Sekar <[email protected]>
| annotations: | ||
| {{- .Annotations | yaml | nindent 4 }} | ||
| {{- end }} | ||
| spec: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
extra indentation here for the spec field.
| MPIStartTimeout int `json:"mpiStartTimeout"` | ||
| } | ||
|
|
||
| type NIMServiceComputeDomainSpec struct{} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
as discussed, we need to handle case of pre-existing CD as well
type NIMServiceComputeDomainSpec struct {
Create *bool `json:"create,omitempty"`
Name string `json:"name,omitempty"`
}
| MPIStartTimeout int `json:"mpiStartTimeout"` | ||
| } | ||
|
|
||
| type NIMServiceComputeDomainSpec struct{} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should be called ComputeDomainSpec
| if n.Spec.MultiNode != nil && n.Spec.MultiNode.Parallelism != nil && n.Spec.MultiNode.Parallelism.Tensor != nil { | ||
| return *n.Spec.MultiNode.Parallelism.Pipeline | ||
| } | ||
| return 0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No part of your change, but can you please update it?
GetMultiNodePipelineParallelism() is looking for n.Spec.MultiNode.Parallelism.Tensornil check instead of n.Spec.MultiNode.Parallelism.Pipeline