Metraipolis › archive › dc_fa57711c1542
Accelerated Dataflow: scaling inference in streaming data analytics with efficiency — arXiv:2610.22731
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22731
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:44:12.287Z
- SHA-256 of the archived text
e1e9f3f1f2800882358fb25900c7d44dc2983b09432e254f6239b50795bfd718- Stable URL of this page
https://metraipolis.com/documento/dc_fa57711c1542
How to cite
Accelerated Dataflow: scaling inference in streaming data analytics with efficiency — arXiv:2610.22731 — arXiv (en), https://arxiv.org/abs/2610.22731 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa57711c1542 (Metraipolis archive dc_fa57711c1542, sha256 e1e9f3f1f2800882358fb25900c7d44dc2983b09432e254f6239b50795bfd718)
BibTeX
@misc{dcfa57711c1542,
title = {Accelerated Dataflow: scaling inference in streaming data analytics with efficiency — arXiv:2610.22731},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22731},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa57711c1542; sha256 e1e9f3f1f2800882358fb25900c7d44dc2983b09432e254f6239b50795bfd718},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22731. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Streaming data analytics helps businesses identify opportunities and spot risks in a timely fashion. As large language model (LLM) usage grows, people are exploring incorporating agents or LLMs in streaming data pipelines to help find patterns in datasets without supervision or interpret natural languages for content moderation. However, most streaming systems are currently optimized for data movement and perform poorly on GPU intensive workloads such as performing inference with LLMs. We introduce a system on Google Cloud Dataflow designed to tackle hybrid streaming machine learning workloads with co-designed autoscaling on heterogeneous worker pools and prefix-aware batching. This increases throughput 1.5x to 2x for streaming pipelines using LLMs while maintaining similar latency with up to 75% peak resource savings and 84% lower peak tail latency compared with existing streaming data processing systems. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2610.22731 — 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 2026-10-19T08:39:39.740Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).