AI Analysis
NVIDIA NIM
Configure NVIDIA NIM for self-hosted model inference
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Configure NVIDIA NIM for self-hosted model inference
kubectl create secret generic nvidia-api-key \
--from-literal=api-key=nvapi-YOUR_KEY \
-n changeguard-system
spec:
ai:
mode: cloud
apiKeySecretRef:
name: nvidia-api-key
spec:
ai:
mode: oncluster
onCluster:
image: "nvcr.io/nim/meta/llama-3.1-70b-instruct:latest"
gpuRequest: "1"
memoryLimit: "80Gi"
spec:
ai:
mode: aws
endpoint: https://your-nim-endpoint.sagemaker.aws