from meetkai_mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.serving.deployments.create(name="llama-3-8b-chat", model="meta-llama/Llama-3.1-8B-Instruct", accelerator={
        "type": "H100",
        "fallback": [
            "H100",
            "MI300X",
        ],
    }, secrets=[
        "hf-token",
    ], engine_args=[
        "--max-model-len",
        "8192",
    ], endpoint_auth=True)

    # Handle response
    print(res)

{
  "id": "<string>",
  "name": "<string>",
  "model": "<string>",
  "accelerator": {
    "type": "<string>",
    "count": 1,
    "fallback": [
      "<string>"
    ]
  },
  "scaling": {
    "min_containers": 0,
    "max_containers": 1,
    "buffer_containers": 0,
    "scaledown_window_s": 300,
    "max_concurrent_inputs": 100
  },
  "image": "<string>",
  "revision": 123,
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "url": "<string>"
}