Skip to content

Commit 6fe810d

Browse files
committed
Renaming the 'base' Criticality band to 'Standard'
1 parent 9d32b34 commit 6fe810d

File tree

2 files changed

+5
-4
lines changed

2 files changed

+5
-4
lines changed

api/v1alpha1/inferencemodel_types.go

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -127,16 +127,17 @@ type PoolObjectReference struct {
127127
// Criticality defines how important it is to serve the model compared to other models.
128128
// Criticality is intentionally a bounded enum to contain the possibilities that need to be supported by the load balancing algorithm. Any reference to the Criticality field must be optional(use a pointer), and set no default.
129129
// This allows us to union this with a oneOf field in the future should we wish to adjust/extend this behavior.
130-
// +kubebuilder:validation:Enum=Critical;Default;Sheddable
130+
// +kubebuilder:validation:Enum=Critical;Standard;Sheddable
131131
type Criticality string
132132

133133
const (
134134
// Critical defines the highest level of criticality. Requests to this band will be shed last.
135135
Critical Criticality = "Critical"
136136

137-
// Default defines the default criticality level and is more important than Sheddable but less
137+
// Standard defines the base criticality level and is more important than Sheddable but less
138138
// important than Critical. Requests in this band will be shed before critical traffic.
139-
Default Criticality = "Default"
139+
// Most models are expected to fall within this band.
140+
Standard Criticality = "Standard"
140141

141142
// Sheddable defines the lowest level of criticality. Requests to this band will be shed before
142143
// all other bands.

config/crd/bases/inference.networking.x-k8s.io_inferencemodels.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ spec:
6464
and the proportionality of fairness will be configurable.
6565
enum:
6666
- Critical
67-
- Default
67+
- Standard
6868
- Sheddable
6969
type: string
7070
modelName:

0 commit comments

Comments
 (0)