Skip to content

Commit 56cffc2

Browse files
committed
Address comments in example deployment
Signed-off-by: Kunjan Patel <[email protected]>
1 parent 62da988 commit 56cffc2

File tree

2 files changed

+8
-1
lines changed

2 files changed

+8
-1
lines changed
+1
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
sidecar/__pycache__/

examples/dynamic-lora-sidecar/deployment.yaml

+7-1
Original file line numberDiff line numberDiff line change
@@ -52,6 +52,13 @@ spec:
5252
value: "gs://vertex-model-garden-public-us/llama2/llama2-7b-hf"
5353
- name: VLLM_ALLOW_RUNTIME_LORA_UPDATING
5454
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"
5562
volumeMounts:
5663
- mountPath: /dev/shm
5764
name: dshm
@@ -74,7 +81,6 @@ spec:
7481
name: dynamic-lora-config
7582
nodeSelector:
7683
cloud.google.com/gke-accelerator: nvidia-l4
77-
cloud.google.com/gke-nodepool: dynamic-lora
7884

7985
---
8086
apiVersion: v1

0 commit comments

Comments
 (0)