Implementation:SeldonIO Seldon core Seldon Model Load

Property	Value
Implementation Name	Seldon_Model_Load
Type	External Tool Doc
Overview	Concrete CLI tool for loading ML models onto Seldon Core 2 inference servers.
Implements Principle	SeldonIO_Seldon_core_Model_Deployment_Execution
Workflow	Model_Deployment
Domains	MLOps, Kubernetes
Source	docs-gb/cli/seldon_model_load.md:L1-30
External Dependencies	seldon CLI, kubectl
Last Updated	2026-02-13 00:00 GMT

Description

The seldon model load command is the primary CLI interface for deploying models onto Seldon Core 2 inference servers. It reads a Model CRD YAML file and submits it to the Seldon scheduler, which initiates the model loading process on a compatible Server. Alternatively, the same effect can be achieved using kubectl apply -f which submits the Model resource through the Kubernetes API.

Code Reference

Source: docs-gb/cli/seldon_model_load.md:L1-30

CLI Signature:

seldon model load -f <model.yaml> [--scheduler-host string] [--force]

Alternative (kubectl):

kubectl apply -f <model.yaml>

Key Parameters

Parameter	Type	Default	Description
-f / --file-path	string	(required)	Path to the Model CRD YAML manifest file
--scheduler-host	string	"0.0.0.0:9004"	Address of the Seldon scheduler gRPC endpoint
--force	boolean	false	Force control plane mode for the load operation
-h / --help	boolean	false	Display help information for the command

I/O Contract

Inputs

Input	Type	Description
Model CRD YAML file	File path	A valid Seldon Core 2 Model manifest (apiVersion: mlops.seldon.io/v1alpha1, kind: Model)
Running Seldon Core 2 cluster	Infrastructure	A Kubernetes cluster with Seldon Core 2 operator and scheduler running

Outputs

Output	Type	Description
Model registration	Scheduler event	Model registered with the Seldon scheduler, loading initiated on a matching Server
Empty JSON response	JSON	{} on successful submission to the scheduler

Usage Examples

Basic Model Load

# Load a model from a YAML manifest
seldon model load -f samples/models/sklearn1.yaml

Load with Custom Scheduler Host

# When scheduler is accessible at a non-default address
seldon model load -f model.yaml --scheduler-host scheduler.seldon-mesh:9004

Load via kubectl

# Submit the Model CRD through the Kubernetes API
kubectl apply -f samples/models/sklearn1.yaml

Full Deployment Workflow

# Step 1: Load the model
seldon model load -f samples/models/sklearn1.yaml

# Step 2: Wait for the model to be ready
seldon model status iris -w ModelAvailable

# Step 3: Send an inference request
seldon model infer iris '{"inputs": [{"name": "predict", "shape": [1, 4], "datatype": "FP32", "data": [[5.1, 3.5, 1.4, 0.2]]}]}'

Knowledge Sources

• Repository: https://github.com/SeldonIO/seldon-core
• Documentation: https://docs.seldon.io/projects/seldon-core/en/v2/

Related Pages

• SeldonIO_Seldon_core_Seldon_Model_Load implements SeldonIO_Seldon_core_Model_Deployment_Execution
• SeldonIO_Seldon_core_Seldon_Model_CRD is consumed by SeldonIO_Seldon_core_Seldon_Model_Load
• SeldonIO_Seldon_core_Seldon_Model_Status follows SeldonIO_Seldon_core_Seldon_Model_Load
• SeldonIO_Seldon_core_Seldon_Model_Infer depends on SeldonIO_Seldon_core_Seldon_Model_Load
• Environment:SeldonIO_Seldon_core_Kubernetes_Cluster_Environment
• Environment:SeldonIO_Seldon_core_Docker_Compose_Local_Environment
• Heuristic:SeldonIO_Seldon_core_Over_Commit_Memory_Tip
• Heuristic:SeldonIO_Seldon_core_Model_Scheduling_Preference_Tip
• Heuristic:SeldonIO_Seldon_core_Model_Load_Timeout_Tip