ModelServe vllmserve-polling Serve

The serve action deploys vLLM models with polling support as services on Kubernetes. A Task is created by calling run() on the Function; task parameters are passed through that call.

Overview

The vllmserve-polling function kind uses the same parameters as vllmserve, with a polling-based serving flow.

Quick example

function = dh.new_function(
    name="my-vllm-polling-service",
    kind="vllmserve-polling",
    url="hf://mistralai/Mistral-7B-v0.1",
)

run = function.run(
    action="serve",
    replicas=1,
)

Parameters

Function Parameters

Must be specified when creating the function.

Name	Type	Description
project	str	Project name. Required only when creating from the library; otherwise MUST NOT be set.
name	str	Name that identifies the object. Required.
kind	str	Function kind. Must be vllmserve-polling. Required.
uuid	str	Object ID in UUID4 format.
description	str	Description of the object.
labels	list[str]	List of labels.
embedded	bool	Whether the object should be embedded in the project.
model_name	str	Name of the model.
image	str	Docker image where to serve the model.
url	str	Model source URL.
adapters	list[dict]	List of adapters.

Adapters

Adapters is a list of dictionaries with the following keys:

adapters = [{
    "name": "adapter-name",
    "url": "adapter-url"
}]

Task Parameters

Can only be specified when calling function.run().

Name	Type	Description
action	str	Task action. Required. Must be serve
node_selector	list[dict]	Node selector.
volumes	list[dict]	List of volumes.
resources	dict	Resource limits/requests.
affinity	dict	Affinity configuration.
tolerations	list[dict]	Tolerations.
envs	list[dict]	Environment variables.
secrets	list[str]	List of secret names.
profile	str	Profile template.
replicas	int	Number of replicas.
service_type	str	Service type.
service_name	str	Service name.

Run Parameters

Can only be specified when calling function.run().

Name	Type	Description
url	str	URL of the vLLM service.
args	list[str]	Extra arguments passed to the vLLM server.
enable_telemetry	bool	Enable or disable telemetry.
use_cpu_image	bool	Use a CPU image for serving.
storage_space	str	Storage space for model artifacts.

Entity methods

Run methods

Once the run is created, you can access its attributes and methods through the run object.

invoke

Invoke served model. The method defaults to "POST" if data or json is provided in kwargs, otherwise it defaults to "GET". The function returns a requests.Response object.

Parameters:

Name	Type	Description	Default
method	str	Method of the request (e.g., "GET", "POST").	'POST'
url	str	URL to invoke. If specified, it must start with the service URL (http:// or https:// prefixes are required and stripped before comparison).	None
**kwargs	dict	Keyword arguments to pass to the request.	{}

Returns:

Type	Description
Response	Response from the request.