Pith. sign in

REVIEW 7 cited by

SLOs-Serve: Optimized Serving of Multi-SLO LLMs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.08784 v1 pith:I5MQMOLE submitted 2025-04-05 cs.DC cs.LG

SLOs-Serve: Optimized Serving of Multi-SLO LLMs

classification cs.DC cs.LG
keywords slos-serveservingalgorithmdynamicmulti-sloacrossallocationallocations
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper introduces SLOs-Serve, a system designed for serving multi-stage large language model (LLM) requests with application- and stage-specific service level objectives (SLOs). The key idea behind SLOs-Serve is to customize the allocation of tokens to meet these SLO requirements. SLOs-Serve uses a multi-SLO dynamic programming-based algorithm to continuously optimize token allocations under SLO constraints by exploring the full design space of chunked prefill and (optional) speculative decoding. Leveraging this resource planning algorithm, SLOs-Serve effectively supports multi-SLOs and multi-replica serving with dynamic request routing while being resilient to bursty arrivals. Our evaluation across 6 LLM application scenarios (including summarization, coding, chatbot, tool calling, and reasoning) demonstrates that SLOs-Serve improves per-GPU serving capacity by 2.2x on average compared to prior state-of-the-art systems.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

    cs.DC 2026-05 unverdicted novelty 7.0

    Dooly reduces LLM inference profiling costs by 56.4% via configuration-agnostic taint-based labeling and selective database reuse, delivering simulation accuracy within 5% MAPE for TTFT and 8% for TPOT across 12 models.

  2. SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

    cs.DC 2026-07 conditional novelty 6.5

    Balancing only first-turn agent requests while keeping follow-ups cache-aware raises LLM cluster TPS 10-16% (colocation) and prefill TPS 2-34% (disaggregation) over SOTA schedulers on production agent traces.

  3. Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving

    cs.DC 2026-07 conditional novelty 6.0

    A Simplex-style guard around untrusted learned admission controllers structurally enforces an assured tenant floor, holding miss 0.0 in real 2xV100 tests where unguarded learners miss 0.86-0.94.

  4. Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

    cs.DC 2026-05 unverdicted novelty 6.0

    Dooly reduces LLM inference profiling GPU-hours by 56.4% across 12 models while keeping simulation MAPE under 5% for TTFT and 8% for TPOT by making profiling configuration-agnostic and redundancy-aware.

  5. Simple is Better: Multiplication May Be All You Need for LLM Request Scheduling

    cs.DC 2026-03 conditional novelty 6.0

    Multiplying new-prefill-token count by instance batch size yields a hyperparameter-free LLM scheduler that matches or beats tuned linear and simulation policies on real production traces.

  6. Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving

    cs.DC 2026-07 conditional novelty 5.5

    Reservation plus assured-first priority holds admitted assured-class miss at 0.0 on real 2xV100 under every miscalibration of a learned admitter, while GAIE Flow Control fails under label swap.

  7. HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling

    cs.DC 2025-08 unverdicted novelty 5.0

    HFX jointly designs scheduling and scaling for multi-SLO LLM serving, achieving up to 4.44x higher SLO attainment, 65.82% lower latency, and 49.81% lower cost than prior systems on multi-task workloads.