Files
edge-gitops/clusters/k3s-dgx/nim-service/qwen.yaml
2026-05-06 17:42:18 -05:00

21 lines
439 B
YAML

apiVersion: apps.nvidia.com/v1alpha1
kind: NIMCache
metadata:
name: qwen3-32b-instruct
namespace: nim-service
spec:
source:
ngc:
modelPuller: nvcr.io/nim/qwen/qwen3-32b-dgx-spark:1.1.0-variant
pullSecret: ngc-secret
authSecret: ngc-api-secret
model:
engine: "vllm"
tensorParallelism: "1"
storage:
pvc:
create: true
size: "100Gi"
volumeAccessMode: ReadWriteOnce
---