We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 62da988 commit 56cffc2Copy full SHA for 56cffc2
examples/dynamic-lora-sidecar/.gitignore
@@ -0,0 +1 @@
1
+sidecar/__pycache__/
examples/dynamic-lora-sidecar/deployment.yaml
@@ -52,6 +52,13 @@ spec:
52
value: "gs://vertex-model-garden-public-us/llama2/llama2-7b-hf"
53
- name: VLLM_ALLOW_RUNTIME_LORA_UPDATING
54
value: "true"
55
+ - name: HF_TOKEN
56
+ valueFrom:
57
+ secretKeyRef:
58
+ name: hf-token # The name of your Kubernetes Secret
59
+ key: HF_TOKEN # The specific key within the Secret
60
+ - name: DYNAMIC_LORA_ROLLOUT_CONFIG
61
+ value: "/config/configmap.yaml"
62
volumeMounts:
63
- mountPath: /dev/shm
64
name: dshm
@@ -74,7 +81,6 @@ spec:
74
81
name: dynamic-lora-config
75
82
nodeSelector:
76
83
cloud.google.com/gke-accelerator: nvidia-l4
77
- cloud.google.com/gke-nodepool: dynamic-lora
78
84
79
85
---
80
86
apiVersion: v1
0 commit comments