Compass: Optimizing Compound AI Workflows for Dynamic Adaptation
Compound AI is a distributed intelligence approach that represents a unified system orchestrating specialized AI/ML models with engineered software components into AI workflows. Compound AI production deployments must satisfy accuracy, latency, and cost objectives under varying loads. However, many deployments operate on fixed infrastructure where horizontal scaling is not viable. Existing approaches optimize solely for accuracy and do not consider changes in workload conditions. We observe that compound AI systems can switch between configurations to fit infrastructure capacity, trading accuracy for latency based on current load. This requires discovering multiple Pareto-optimal configurations from a combinatorial search space and determining when to switch between them at runtime. We present Compass, a novel framework that enables dynamic configuration switching through offline optimization and online adaptation. Compass consists of three components: COMPASS-V algorithm for configuration discovery, Planner for switching policy derivation, and Elastico Controller for runtime adaptation. COMPASS-V discovers accuracy-feasible configurations using finite-difference guided search and a combination of hill-climbing and lateral expansion. Planner profiles these configurations on target hardware and derives switching policies using a queuing theory based model. Elastico monitors queue depth and switches configurations based on derived thresholds. Across two compound AI workflows, COMPASS-V achieves 100% recall while reducing configuration evaluations by 57.5% on average compared to exhaustive search, with efficiency gains reaching 95.3% at tight accuracy thresholds. Runtime adaptation achieves 90-98% SLO compliance under dynamic load patterns, improving SLO compliance by 71.6% over static high-accuracy baselines, while simultaneously improving accuracy by 3-5% over static fast baselines.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions
Recent advancements in large language models (LLMs) and AI systems have led to a paradigm shift in the design and optimization of complex AI workflows. By integrating multiple components, compound AI systems have become …
Reinforcement Learning (RL)Uncovering Bottlenecks and Optimizing Scientific Lab Workflows with Cycle Time Reduction Agents
Scientific laboratories, particularly those in pharmaceutical and biotechnology companies, encounter significant challenges in optimizing workflows due to the complexity and volume of tasks such as compound screening and…
Domain specialization: a post-training domain adaptation for Neural Machine Translation
Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human post-editing workflows in Computer Assisted Translation (CAT). With Neura…
Domain AdaptationMachine TranslationNMTTranslationLarge Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey
Building effective machine learning (ML) workflows to address complex tasks is a primary focus of the Automatic ML (AutoML) community and a critical step toward achieving artificial general intelligence (AGI). Recently, …
AutoMLFeature EngineeringHyperparameter OptimizationModel SelectionOptimizing Numerical Estimation and Operational Efficiency in the Legal Domain through Large Language Models
The legal landscape encompasses a wide array of lawsuit types, presenting lawyers with challenges in delivering timely and accurate information to clients, particularly concerning critical aspects like potential imprison…
Mathematical Reasoning