Metraipolis › archive › dc_8bfa0eacf0e2
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters — arXiv:2609.04513
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04513
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:26:27.306Z
- SHA-256 of the archived text
e6449987604268128eb05cf5b96d34fb9fc689096bf10401d496c707dd09d36b- Stable URL of this page
https://metraipolis.com/documento/dc_8bfa0eacf0e2
How to cite
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters — arXiv:2609.04513 — arXiv (en), https://arxiv.org/abs/2609.04513 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bfa0eacf0e2 (Metraipolis archive dc_8bfa0eacf0e2, sha256 e6449987604268128eb05cf5b96d34fb9fc689096bf10401d496c707dd09d36b)
BibTeX
@misc{dc8bfa0eacf0e2,
title = {Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters — arXiv:2609.04513},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04513},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bfa0eacf0e2; sha256 e6449987604268128eb05cf5b96d34fb9fc689096bf10401d496c707dd09d36b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04513. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Compound AI workflows are increasingly used to serve complex AI tasks by coordinating multiple AI models and software components. This approach enables deployment flexibility, as each workflow stage can expose different model variants and resource requirements, but it also expands the deployment choices. A deployment must choose an execution plan that selects AI models for each compound AI workflow stage and places them on a heterogeneous cluster in order to satisfy SLOs. Deployment optimizers therefore need estimates to compare many candidate plans and identify feasible ones. System metrics can often be profiled per stage and composed according to workflow topology, but accuracy cannot, as errors and information loss at upstream stages affect the accuracy of downstream stages. Existing approaches either profile complete configurations end to end, which scales poorly, or use product-based accuracy surrogates that treat stages as independent and can misrank candidate plans. We introduce Atlas, a framework for optimizing compound AI deployments under SLO constraints. Atlas uses MAP, a Markovian Accuracy Predictor, to estimate configuration accuracy from local conditional accuracy transitions between adjacent workflow stages. MAP discretizes intermediate outputs into accuracy buckets and composes transition profiles according to workflow topology, giving the optimizer an accuracy estimate without exhaustive end-to-end profiling. Atlas formulates execution-plan selection as a mixed-integer linear program that maximizes predicted accuracy subject to SLOs. Across four compound AI workflows, MAP achieves Spearman correlation up to 0.947 while reducing profiling cost by up to 2.6x relative to exhaustive end-to-end profiling. Guided by MAP, the Atlas optimizer selects execution plans within 0.03 of oracle accuracy while reducing deployment cost by up to 42% through heterogeneous placement. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.04513 — 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 2026-10-16T22:18:11.501Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).