Skip to content

Commit 5895cc3

Browse files
committed
grammatical fixes
1 parent bb516eb commit 5895cc3

File tree

2 files changed

+4
-8
lines changed

2 files changed

+4
-8
lines changed

api/v1alpha1/inferencemodel_types.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -90,9 +90,9 @@ type InferenceModelSpec struct {
9090
// - A model server serving `llama2-7b` may be represented by:
9191
// - setting the modelName to `llama2-7b` and setting no targetModels
9292
// - setting the modelName to `hello-world` and setting a single targetModel to `llama2-7b`, and setting no weights
93-
// - setting modelName to 'my-fine-tune' setting 2 targetModels 'fine-tune-v1' & 'fine-tune-v2' and setting no weights.
93+
// - setting modelName to 'my-fine-tune', setting 2 targetModels 'fine-tune-v1' & 'fine-tune-v2', and setting no weights.
9494
// This has the effect of weighing the two models equally
95-
// - setting modelName to 'my-fine-tune' setting 2 targetModels 'fine-tune-v1' w/weight: 10 & 'fine-tune-v2' w/weight: 1.
95+
// - setting modelName to 'my-fine-tune', setting 2 targetModels 'fine-tune-v1' w/weight: 10 & 'fine-tune-v2' w/weight: 1.
9696
// This has the effect of the fine-tune-v1 being selected 10x as often as v2
9797
//
9898
// +optional

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

Lines changed: 2 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -69,10 +69,6 @@ spec:
6969
criticality:
7070
description: |-
7171
Criticality defines how important it is to serve the model compared to other models referencing the same pool.
72-
Criticality impacts how traffic is handled in resource constrained situations. It handles this by
73-
queuing or rejecting requests of lower criticality. InferenceModels of an equivalent Criticality will
74-
fairly share resources over throughput of tokens. In the future, the metric used to calculate fairness,
75-
and the proportionality of fairness will be configurable.
7672
7773
Default values for this field will not be set, to allow for future additions of new field that may 'one of' with this field.
7874
Any implementations that may consume this field may treat an unset value as the 'Standard' range.
@@ -127,9 +123,9 @@ spec:
127123
- A model server serving `llama2-7b` may be represented by:
128124
- setting the modelName to `llama2-7b` and setting no targetModels
129125
- setting the modelName to `hello-world` and setting a single targetModel to `llama2-7b`, and setting no weights
130-
- setting modelName to 'my-fine-tune' setting 2 targetModels 'fine-tune-v1' & 'fine-tune-v2' and setting no weights.
126+
- setting modelName to 'my-fine-tune', setting 2 targetModels 'fine-tune-v1' & 'fine-tune-v2', and setting no weights.
131127
This has the effect of weighing the two models equally
132-
- setting modelName to 'my-fine-tune' setting 2 targetModels 'fine-tune-v1' w/weight: 10 & 'fine-tune-v2' w/weight: 1.
128+
- setting modelName to 'my-fine-tune', setting 2 targetModels 'fine-tune-v1' w/weight: 10 & 'fine-tune-v2' w/weight: 1.
133129
This has the effect of the fine-tune-v1 being selected 10x as often as v2
134130
items:
135131
description: |-

0 commit comments

Comments
 (0)