Implementation:Triton inference server Server L0 Sagemaker Test

Knowledge Sources	Triton Inference Server
Domains	Testing, Cloud_Integration
Last Updated	2026-02-13 17:00 GMT

Overview

QA test script for validating SageMaker endpoint compatibility in the Triton Inference Server.

Description

This test validates the Triton Inference Server's compatibility with the AWS SageMaker hosting interface. It verifies that the server correctly implements the SageMaker-specific HTTP endpoints including the ping health check and invocations endpoint, that model loading from the SageMaker-expected directory structure works correctly, and that inference requests using the SageMaker payload format produce correct results. The test also validates multi-model endpoint behavior and the SAGEMAKER_TRITON environment variable configuration.

Usage

Run as part of the Triton QA test suite. Requires a GPU-enabled Docker environment with pre-generated test models.

Code Reference

Source Location

• Repository: Triton Inference Server
• File: qa/L0_sagemaker/test.sh
• Lines: 1-624

Signature

#!/bin/bash
source ../common/util.sh
# Test orchestration for SageMaker endpoint compatibility

Import

source ../common/util.sh

I/O Contract

Inputs

Name	Type	Required	Description
DATADIR	env var	No	Test data directory
MODEL_REPO	directory	Yes	Test model repository

Outputs

Name	Type	Description
exit code	int	0 on success, 1 on failure
test logs	files	Server and test output logs

Usage Examples

Running the Test

cd qa/L0_sagemaker/
bash test.sh

Related Pages

• Environment:Triton_inference_server_Server_GPU_CUDA_Runtime