P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving

[2608.15171] P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Distributed, Parallel, and Cluster Computing arXiv:2608.15171 (cs) [Submitted on 15 Aug 2026] Title: P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving Authors: Timo Sämann View a PDF of the paper titled P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving, by Timo S\"amann View PDF HTML (experimental) Abstract: Long-context LLM applications such as retrieval-augmented generation (RAG) and agentic systems often process tens of thousands of input tokens to produce short outputs, making end-to-end request latency an important serving objective. We show that the maximum number of batched tokens (MBT), which controls the token scheduling budget in vLLM, has a scheduling-pressure-dependent effect on latency. Larger token budgets can reduce latency under low scheduling pressure, while smaller budgets become preferable under higher pressure. Consequently, no single static MBT performs best across load regimes. We introduce Prefill-Pressure Adaptive Scheduling (P-PAS), a lightweight policy that dynamically adapts the scheduling budget based on concurrent prefill and decode state. P-PAS retains a large token budget under low pressure and constrains prefill work as pressure increases. Across models, workloads, and GPUs, P-PAS maintains low end-to-end latency across changing load regimes, avoiding the limitations of a fixed MBT. Kernel-level profiling shows that large prefill chunks can improve execution efficiency under low scheduling pressure, but that this advantage varies across model--hardware configurations. As scheduling pressure increases, smaller chunks can instead reduce interference with active decoding, explaining the observed load-dependent MBT sensitivity. Code and artifacts for reproducing our results are available at this https URL . Subjects: Distributed, Parallel, and Cluster Computing (cs.DC) Cite as: arXiv:2608.15171 [cs.DC] (or arXiv:2608.15171v1 [cs.DC] for this version) https://doi.org/10.48550/arXiv.2608.15171 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Timo Sämann PhD [ view email ] [v1] Sat, 15 Aug 2026 11:18:42 UTC (912 KB) Full-text links: Access Paper: View a PDF of the paper titled P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving, by Timo S\"amann View PDF HTML (experimental) TeX Source view license Current browse context: cs.DC < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving#611117
• P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving#459630
• Coordinated Scheduling for MoE LLM Serving#280179
• LEO-Aware DRL Meta-Scheduler for 5G Non-Terrestrial Network Slicing#423895
• Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving#267618