Compass: SLO-aware Query Planner for Compound AI Serving at Scale
Summary: Compass is an SLO-aware planner for compound AI pipelines, jointly optimizing operator placement, configuration, and resources across cloud–edge deployments. It scales via problem decomposition, plan reuse, selective profiling, and runtime query-plan matching under contention. (summarized by gpt-5.6-luna on Aug 17 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Banruo Liu (University of Illinois Urbana-Champaign)
- 2. Wei-Yu Lin (Independent)
- 3. Minghao Fang (University of Illinois Urbana-Champaign)
- 4. Yihan Jiang (University of Illinois Urbana-Champaign)
- 5. Fan Lai (University of Illinois Urbana-Champaign)
BibTeX Citation
@article{liu_vldb26,
title = {{Compass: SLO-aware Query Planner for Compound AI Serving at Scale}},
author = {Liu, Banruo and Lin, Wei-Yu and Fang, Minghao and Jiang, Yihan and Lai, Fan},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {9},
pages = {1921--1934},
doi = {10.14778/3819518.3819524},
url = {https://doi.org/10.14778/3819518.3819524},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 78 | Automatic Database Management System Tuning Through Large-scale Machine Learning | 2017 | SIGMOD | 0.00036684414 |
| 3,508 | Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures | 2023 | VLDB | 7.2490197e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 12,069 | Serverless Query Processing on a Budget | 2020 | SIGMOD |
| 2 | 11,393 | Smart SPARQL Advisor: Guiding Users in Query Formulation with Performance Prediction | 2025 | VLDB |
| 3 | 2,834 | Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings | 2020 | SIGMOD |
| 4 | 10,755 | A Resource-centric Analysis and Optimization of NoSQL Workloads using Distressed Resource Volume Metric | 2026 | VLDB |
| 5 | 10,817 | A Unified Query Planning Framework for Conjunctive Regular Path Queries | 2026 | VLDB |
| 6 | 13,581 | OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration | 2026 | VLDB |
| 7 | 9,954 | Conformal Prediction for Verifiable Learned Query Optimization | 2025 | VLDB |
| 8 | 8,213 | Scaling a Declarative Cluster Manager Architecture with Query Optimization Techniques | 2023 | VLDB |
| 9 | 3,949 | Deploying a Steered Query Optimizer in Production at Microsoft | 2022 | SIGMOD |
| 10 | 5,003 | COMPASS: Online Sketch-based Query Optimization for In-Memory Databases | 2021 | SIGMOD |