Metraipolis › archive › dc_9fee32b82259
GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading — arXiv:2610.38196
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38196
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:18:58.015Z
- SHA-256 of the archived text
d7d8e8dfa11a7a3db8ec29cda1e1003844f3aa097657107a222ab087a8dcf4dd- Stable URL of this page
https://metraipolis.com/documento/dc_9fee32b82259
How to cite
GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading — arXiv:2610.38196 — arXiv (en), https://arxiv.org/abs/2610.38196 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fee32b82259 (Metraipolis archive dc_9fee32b82259, sha256 d7d8e8dfa11a7a3db8ec29cda1e1003844f3aa097657107a222ab087a8dcf4dd)
BibTeX
@misc{dc9fee32b82259,
title = {GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading — arXiv:2610.38196},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38196},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fee32b82259; sha256 d7d8e8dfa11a7a3db8ec29cda1e1003844f3aa097657107a222ab087a8dcf4dd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38196. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Serverless platforms increasingly host machine learning (ML) inference workflows, modeled as directed acyclic graphs (DAGs) of interdependent functions. Beyond container startup, each ML node must load libraries, model weights, and CUDA kernels before it can run. These costs accumulate along dependent DAG paths and place initialization on the end-to-end critical path. Existing systems optimize one half of this problem. DAG-agnostic pre-loading prepares nodes the request may never reach, wasting host and GPU memory. DAG-aware serving routes and scales whole functions, leaving the loading stages inside a node untouched. This paper presents GearUp, a serverless DAG inference serving system that removes ML-node loading from the end-to-end critical path at low resource cost. GearUp profiles the loading stages of each node and schedules them inside the slack time the DAG exposes, hiding initialization behind upstream execution. It reuses initialized instances within and across requests to avoid redundant cold starts. A probabilistic, traffic-adaptive keep-alive policy sets how long idle instances are retained, balancing memory cost against cold-start risk under bursty load. On the AMBER Alert and FINRA-ML workflows with NVIDIA L40S GPUs, GearUp reduces median end-to-end latency by 64.5% and 75.9% against SMIless, for median speedups of 3.1x and 10.0x over cold execution. Integrated GPU and host memory allocation fall by up to 83.9% and 94.6% against eager pre-loading in InstaInfer. GearUp achieves 4.2x strong scaling on four workers. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (cs.LG); Operating Systems (cs.OS). Pagina del lavoro: https://arxiv.org/abs/2610.38196 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T06:07:53.366Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).