Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2511.13728

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

Maximilian Reisecker·Cynthia Marcelino·Thomas Pusztai·Stefan Nastic
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

cs.DC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Maximilian Reisecker, Cynthia Marcelino, Thomas Pusztai, Stefan Nastic. 2025-11-01. Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum. https://doi.org/10.1145/3773276.3774299

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

The HEAL Data Platform

Objective: The objective was to develop a cloud-based, federated system to serve as a single point of search, discovery and analysis for data generated under the NIH Helping to End Addiction Long-term (HEAL) Initiative. Materials and methods: The HEAL Data Platform is built on the open source Gen3 platform, utilizing a small set of framework services and exposed APIs to interoperate with both NIH and non-NIH data repositories. Framework services include those for authentication and authorization, creating persistent identifiers for data objects, and adding and updating metadata. Results: The HEAL Data Platform serves as a single point of discovery of over one thousand studies funded under the HEAL Initiative. With hundreds of users per month, the HEAL Data Platform provides rich metadata and currently interoperates with nineteen data repositories and commons to provide access to shared datasets. Secure, cloud-based compute environments that are integrated with STRIDES facilitate secondary analysis of HEAL data. Discussion: Studies funded under the HEAL Initiative generate a wide variety of data types, which are deposited across multiple NIH and third-party data repositories. The mesh architecture of the HEAL Data Platform provides a single point of discovery of these data resources, accelerating and facilitating secondary use. Conclusion: The HEAL Data Platform enables search, discovery, and analysis of data that are deposited in connected data repositories and commons. By ensuring that these data are fully Findable, Accessible, Interoperable and Reusable (FAIR), the HEAL Data Platform maximizes the value of data generated under the HEAL Initiative.

cs.DC↗
arXiv2026

Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication Overlap

Mixture-of-Experts (MoE) inference under expert parallelism (EP) turns each MoE layer into a distributed computation with costly dispatch and combine communication. State-of-the-art systems reduce this cost through communication-computation overlap, splitting the GPU's SMs for communication and computation respectively. However, this approach still leaves GPU resources wasted along two dimensions. Spatially, the best SM split is determined by each layer's routing result and varies across layers and GPUs, so fixed policies mismatch the workload and waste either NVLink bandwidth or compute throughput. Temporally, complex MoE data dependencies introduce bubbles that leave SMs idle. We present Weave, to our knowledge the first MoE overlap system that performs fine-grained dynamic SM scheduling - deciding per layer and per GPU by routing results at runtime. Once routing completes, each layer's communication and computation volumes become known; Weave exploits this predictability through a lightweight cost model running inside the persistent megakernel: a spatial scheduler partitions SMs into communication workers and computation workers to match the communication/computation throughput ratio, and a temporal scheduler coordinates the two worker groups to minimize SM idleness. On 4x H100 SXM GPUs across six mainstream MoE models, Weave achieves a 2.89x geometric-mean MoE-layer speedup and a 1.33x geometric-mean end-to-end speedup over five state-of-the-art baselines.

cs.DC↗
arXiv2026

pytest-gpu-proof: Enabling Cloud-CPU Continuous Integration for GPU Code with Local GPU Attestation

GPU acceleration is now routine across robotics, but cloud-hosted GPU continuous integration (CI) runners are expensive, resulting in severe under-testing of GPU-accelerated code. We present pytest-gpu-proof, an open-source pytest plugin offering a practical middle ground. Tests can be run on a local machine, signed with a receipt of exactly what ran and what it produced, and integrated into standard CPU CI workflows (e.g., GitHub Actions). The tool is open source and on PyPI, and we are actively integrating it across our lab's software stack.

cs.DC↗