Metraipolis › archive › dc_fdf164f59630

Ripple: Deadline-Aware CPU-GPU Sharing for Embodied Inference — arXiv:2611.01067

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01067
License (as archived)
CC0-1.0
Archived
2026-11-03T11:05:41.353Z
SHA-256 of the archived text
4575ea5ecab8fbbf25e71d1ed98cb52749d61837d3b5707d732163534d181abd
Stable URL of this page
https://metraipolis.com/documento/dc_fdf164f59630

How to cite

Ripple: Deadline-Aware CPU-GPU Sharing for Embodied Inference — arXiv:2611.01067 — arXiv (en), https://arxiv.org/abs/2611.01067 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdf164f59630 (Metraipolis archive dc_fdf164f59630, sha256 4575ea5ecab8fbbf25e71d1ed98cb52749d61837d3b5707d732163534d181abd)
BibTeX
@misc{dcfdf164f59630,
  title = {Ripple: Deadline-Aware CPU-GPU Sharing for Embodied Inference — arXiv:2611.01067},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01067},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdf164f59630; sha256 4575ea5ecab8fbbf25e71d1ed98cb52749d61837d3b5707d732163534d181abd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01067. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unified-memory edge devices increasingly run LLM/VLM inference alongside time-critical CPU tasks for perception and control. GPU memory traffic can overwhelm these tasks, yet platforms such as DGX Spark expose neither bandwidth counters nor direct bandwidth regulation. We present Ripple, a CPU-GPU co-scheduler that combines model-derived GPU memory volumes with CPU completion feedback to regulate interference. Ripple divides inference into pausable, layer-based units and translates each CPU job's deadline slack into a GPU-byte budget, admitting work within the budgets of all overlapping jobs. Online updates track changing interference, while deadline-aware pacing and judicious SM footprint narrowing preserve inference progress. Implemented with SGLang engine hooks and a central scheduler, we evaluate Ripple on DGX Spark with four robotic CPU task mixes and LLM/VLM inference. It is the only evaluated approach that consistently meets the 2% CPU deadline-miss target and VLM deadlines across the tested deadline settings while retaining best-effort LLM throughput.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI); Operating Systems (cs.OS); Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2611.01067 — 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 2026-11-03T10:59:45.989Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).