Implementation:Triton inference server Server L0 Storage S3 Test

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

Overview

QA test script for validating S3 storage backend for model loading in the Triton Inference Server.

Description

This test validates the Triton Inference Server's ability to load and serve models stored in Amazon S3-compatible object storage. It verifies that models can be loaded from S3 bucket paths, that model repository polling detects changes in S3, and that authentication credentials are correctly used for accessing private buckets. The test covers both AWS S3 and S3-compatible endpoints such as MinIO, and validates model versioning, subdirectory structures, and large model file transfers from cloud storage.

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_storage_S3/test.sh
• Lines: 1-531

Signature

#!/bin/bash
source ../common/util.sh
# Test orchestration for S3 storage backend for model loading

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_storage_S3/
bash test.sh

Related Pages

• Environment:Triton_inference_server_Server_GPU_CUDA_Runtime