Implementation:Triton inference server Server L0 Rate Limiter Test

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

Overview

QA test script for validating request rate limiting in the Triton Inference Server.

Description

This test validates the Triton Inference Server's rate limiter functionality, which controls the rate at which inference requests are dispatched to model instances. It verifies that resource constraints are respected, that execution counts across model instances reflect the configured rate-limit priorities, and that the rate limiter correctly manages shared and per-instance resource budgets. The test exercises both single-model and multi-model scenarios to ensure fair scheduling under contention.

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_rate_limiter/test.sh
• Lines: 1-472

Signature

#!/bin/bash
source ../common/util.sh
# Test orchestration for request rate limiting

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_rate_limiter/
bash test.sh

Related Pages

• Environment:Triton_inference_server_Server_GPU_CUDA_Runtime