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 4ff391b commit f4c956cCopy full SHA for f4c956c
config/manifests/gateway/httproute-with-timeout.yaml
@@ -11,7 +11,7 @@ spec:
11
- backendRefs:
12
- group: inference.networking.x-k8s.io
13
kind: InferencePool
14
- name: vllm-llama2-7b
+ name: vllm-llama3-8b-instruct
15
matches:
16
- path:
17
type: PathPrefix
config/manifests/gateway/httproute.yaml
config/manifests/inferencemodel.yaml
@@ -8,7 +8,7 @@ spec:
8
poolRef:
9
name: vllm-llama3-8b-instruct
10
targetModels:
- - name: food-review-1
+ - name: food-review
weight: 100
---
0 commit comments