We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 5f191fc commit aa6b666Copy full SHA for aa6b666
config/samples/isvc/meta/llama3-1-8b-instruct.yaml
@@ -0,0 +1,23 @@
1
+# ---
2
+# apiVersion: v1
3
+# kind: Namespace
4
+# metadata:
5
+# name: llama-3-1-8b-instruct
6
+---
7
+
8
+apiVersion: ome.io/v1beta1
9
+kind: InferenceService
10
+metadata:
11
+ name: llama-3-1-8b-instruct
12
+ namespace: llama-3-1-8b-instruct
13
+spec:
14
+ model:
15
16
+ engine:
17
+ minReplicas: 8
18
+ maxReplicas: 8
19
+ runtime:
20
+ name: srt-llama-3-1-8b-instruct
21
+ router:
22
+ minReplicas: 1
23
+ maxReplicas: 1
0 commit comments