$ export NGC_API_KEY=<value> # ngc 的 api key$ echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin
$ docker pull nvcr.io/nim/meta/llama3-8b-instruct:1.0.0$ docker tag nvcr.io/nim/meta/llama3-8b-instruct:1.0.0 <your-cr-host>/<your-cr-namespace>/llama3-8b-instruct:1.0.0
$ echo "<your-cr-password>" | docker login --username=<account-name>@<account-id> <your-cr-host>$ docker push <your-cr-host>/<your-cr-namespace>/llama3-8b-instruct:1.0.0

$ git clone https://github.com/NVIDIA/nim-deploy.git$ cd nim-deploy/helm/nim-llmhelm registry login --username=<account-name>@<account-id> <your-cr-host>helm package ./ --version 0.2.1helm push nim-llm-0.2.1.tgz oci://<your-cr-host>/<your-cr-namespace>

image:# Adjust to the actual location of the image and version you wantrepository: <your-cr-host>/<your-cr-namespace>/llama3-8b-instructtag: 1.0.0model:name: meta/llama3-8b-instruct # not strictly necessary, but enables running "helm test" belowngcAPISecret: ngc-apingcAPIKey: "<your-ngc-api-key>"persistence:enabled: truestorageClass: "<your-nas-storage-class>"annotations:helm.sh/resource-policy: keepstatefulSet:enabled: falsemetrics:enabled: trueserviceMonitor:# for use with the Prometheus Operator and the primary service objectenabled: trueadditionalLabels: volcengine.vmp: "true"service:type: LoadBalancerpodAnnotations:vci.vke.volcengine.com/preferred-instance-family: vci.gni2 #规格按模型和region情况具体选择，参考https://www.volcengine.com/docs/6460/76911选择适配规格vke.volcengine.com/burst-to-vci: enforceresources:limits:nvidia.com/gpu: 1

INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

$ curl -X 'POST' \'http://<lb-ip>:8000/v1/chat/completions' \-H 'accept: application/json' \-H 'Content-Type: application/json' \-d '{"messages": [{"content": "You are a polite and respectful chatbot helping people plan a vacation.","role": "system"},{"content": "What should I do for a 4 day vacation in Spain?","role": "user"}],"model": "meta/llama3-8b-instruct","max_tokens": 16,"top_p": 1,"n": 1,"stream": false,"stop": "\n","frequency_penalty": 0.0}'

{"id":"cmpl-a98bbfec02ab4771a3d6ad81caf63e94","object":"chat.completion","created":1718878017,"model":"meta/llama3-8b-instruct","choices":[{"index":0,"message":{"role":"assistant","content":"¡hola! Spain is a wonderful destination, and I'd be delighted to"},"logprobs":null,"finish_reason":"length","stop_reason":null}],"usage":{"prompt_tokens":42,"total_tokens":58,"completion_tokens":16}}