Skip to content

Chore: Deprecate desiredOptimizedAlloc.accelerator #955

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.

Sign up for GitHub

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

Merged
github-actions merged 9 commits into from
Mar 31, 2026
Merged

Chore: Deprecate desiredOptimizedAlloc.accelerator #955

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
227adac
Add shuynh2017 to the OWNERS list
shuynh2017 Mar 17, 2026
34811b6
Merge branch 'llm-d:main' into main
shuynh2017 Mar 18, 2026
3dc488f
Merge branch 'llm-d:main' into main
shuynh2017 Mar 21, 2026
d6988bb
Merge branch 'llm-d:main' into main
shuynh2017 Mar 24, 2026
031dff3
Merge branch 'llm-d:main' into main
shuynh2017 Mar 27, 2026
327dc8a
Merge branch 'llm-d:main' into main
shuynh2017 Mar 28, 2026
5bd0073
deprecate desiredOptimizedAlloc.accelerator
shuynh2017 Mar 30, 2026
444132d
make optional
shuynh2017 Mar 30, 2026
63ca43f
remove MinLength
shuynh2017 Mar 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions api/v1alpha1/variantautoscaling_types.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,8 +72,9 @@ type OptimizedAlloc struct {
LastRunTime metav1.Time `json:"lastRunTime,omitempty"`

// Accelerator is the type of accelerator for the optimized allocation.
// +kubebuilder:validation:MinLength=2
Accelerator string `json:"accelerator"`
// Deprecated: This field is deprecated and will be removed in a future version. Use node selector or node affinity from scale target instead.
// +optional
Accelerator string `json:"accelerator,omitempty"`

// NumReplicas is the number of replicas for the optimized allocation.
// nil means no optimization decision has been made yet.
Expand Down
8 changes: 3 additions & 5 deletions charts/workload-variant-autoscaler/crds/llmd.ai_variantautoscalings.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,9 +201,9 @@ spec:
allocation based on autoscaling logic.
properties:
accelerator:
description: Accelerator is the type of accelerator for the optimized
allocation.
minLength: 2
description: |-
Accelerator is the type of accelerator for the optimized allocation.
Deprecated: This field is deprecated and will be removed in a future version. Use node selector or node affinity from scale target instead.
type: string
lastRunTime:
description: LastRunTime is the timestamp of the last optimization
Expand All @@ -217,8 +217,6 @@ spec:
format: int32
minimum: 0
type: integer
required:
- accelerator
type: object
type: object
type: object
Expand Down
8 changes: 3 additions & 5 deletions config/crd/bases/llmd.ai_variantautoscalings.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,9 +201,9 @@ spec:
allocation based on autoscaling logic.
properties:
accelerator:
description: Accelerator is the type of accelerator for the optimized
allocation.
minLength: 2
description: |-
Accelerator is the type of accelerator for the optimized allocation.
Deprecated: This field is deprecated and will be removed in a future version. Use node selector or node affinity from scale target instead.
type: string
lastRunTime:
description: LastRunTime is the timestamp of the last optimization
Expand All @@ -217,8 +217,6 @@ spec:
format: int32
minimum: 0
type: integer
required:
- accelerator
type: object
type: object
type: object
Expand Down
2 changes: 1 addition & 1 deletion docs/user-guide/crd-reference.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ _Appears in:_
| Field | Description | Default | Validation |
| --- | --- | --- | --- |
| `lastRunTime` _[Time](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.32/#time-v1-meta)_ | LastRunTime is the timestamp of the last optimization run. | | |
| `accelerator` _string_ | Accelerator is the type of accelerator for the optimized allocation. | | MinLength: 2 <br /> |
| `accelerator` _string_ | Accelerator is the type of accelerator for the optimized allocation. This field is deprecated and will be removed in a future version. Use node selector or node affinity from scale target instead. | | MinLength: 2 <br /> |
| `numReplicas` _integer_ | NumReplicas is the number of replicas for the optimized allocation.<br />nil means no optimization decision has been made yet. | | Minimum: 0 <br /> |


Expand Down
Loading