Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum

TL;DR

Gaia introduces a dynamic GPU management system for serverless AI workloads in heterogeneous environments, significantly reducing latency and improving efficiency by adaptively selecting optimal hardware acceleration modes.

Contribution

Gaia presents a novel platform-level GPU-as-a-service architecture with adaptive runtime management for serverless AI in the 3D compute continuum.

Findings

Reduces end-to-end latency by up to 95%.

Effectively selects optimal hardware acceleration modes.

Enables SLO-aware, cost-efficient serverless AI execution.

Abstract

Serverless computing offers elastic scaling and pay-per-use execution, making it well-suited for AI workloads. As these workloads run in heterogeneous environments such as the Edge-Cloud-Space 3D Continuum, they often require intensive parallel computation, which GPUs can perform far more efficiently than CPUs. However, current platforms struggle to manage hardware acceleration effectively, as static user-device assignments fail to ensure SLO compliance under varying loads or placements, and one-time dynamic selections often lead to suboptimal or cost-inefficient configurations. To address these issues, we present Gaia, a GPU-as-a-service model and architecture that makes hardware acceleration a platform concern. Gaia combines (i) a lightweight Execution Mode Identifier that inspects function code at deploy time to emit one of four execution modes, and a Dynamic Function Runtime that continuously reevaluates user-defined SLOs to promote or demote between CPU- and GPU backends. Our evaluation shows that it seamlessly selects the best hardware acceleration for the workload, reducing end-to-end latency by up to 95%. These results indicate that Gaia enables SLO-aware, cost-efficient acceleration for serverless AI across heterogeneous environments.