arXiv subjects

Mario Colosi

Publications and source records attributed to Mario Colosi.

5 recordsLinked to original sources

arXiv2026

DRLM: Deep Reinforcement Learning-Based LLM Query Orchestration in Edge Environments

Large language model (LLM) services increasingly process heterogeneous queries with diverse latency, accuracy, and resource requirements. While edge deployment reduces response time, the heterogeneity of devices and the diversity of model families, parameter scales, and quantization levels make efficient LLM query orchestration challenging. This paper introduces DRLM, a Deep Reinforcement Learning-based LLM query orchestration framework in edge environments. DRLM integrates two lightweight predictors: (i) a class-conditioned quality estimator that maps queries to semantic categories and infers model performance, and (ii) a feature-driven latency predictor that estimates inference time across model-device configurations. These predictions, combined with system state, feed a factorized Proximal Policy Optimization (PPO) agent that performs state-aware orchestration decisions. To enable data-driven orchestration, we construct a large-scale benchmarking dataset with 223 835 measurements spanning 1258 queries, 6 query classes, 8 model families (32 deployed instances), 5 quantization levels, and heterogeneous edge devices. Evaluation on a 64-node edge cluster and comparison with three baselines and two state-of-the-art methods show that DRLM reduces inference latency by up to 51% and queuing delay by up to 67 %, while incurring at most 8% accuracy loss. It improves latency under increasing workloads up to 61.4%, demonstrating robust and stable orchestration.

cs.DC↗

arXiv2026

LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters

Large language model (LLM) services increasingly operate on edge infrastructure, enabling low-latency and privacy-preserving AI services. However, efficiently serving LLM requests across heterogeneous and resource-constrained edge devices require orchestration mechanisms that jointly determine model configuration (family, size, and quantization level) and execution placement while satisfying user- and system-level quality of service (QoS) requirements. This paper introduces LMEdge, a QoS-aware orchestration service that dynamically makes these decisions across heterogeneous edge devices. We formulate the problem as a binary integer linear programming (BILP) optimization that minimizes response time under accuracy, network, and resource constraints. To enable scalable online scheduling, we employ five lightweight machine learning (ML) models to predict query-specific latency, accuracy, resource usage, and response size for each model-size-quantization-device combination, and design a lightweight heuristic that approximates the BILP solution. We collect a comprehensive benchmarking dataset of over 59000 rows to train models and support reproducibility. Evaluation on a Kubernetes-based edge testbed with 57 instances and diverse query categories shows that LMEdge reduces latency, preserves accuracy, improves resource utilization, and increases serving ratio compared to two baselines.

cs.DC↗

arXiv2026

ClusterLess: Deadline-Aware Serverless Workflow Orchestration on Federated Edge Clusters

The recent convergence of edge computing, serverless execution, and Kubernetes (K8s) based container orchestration has enabled the processing of application workflows close to data sources. While effective within a single edge cluster, existing schemes do not generalize to federated multi edge environments, where multiple workflows execute concurrently under strict end to end (E2E) deadline constraints. This paper introduces ClusterLess, a deadline aware serverless workflow orchestration method for federated multi edge K8s clusters. ClusterLess manages the E2E lifecycle of workflow execution, including dependency analysis, execution mode selection, and resource aware placement. To this end, it integrates structured intra cluster orchestration with a leader selected, super master driven intercluster coordination layer, determining where and how each workflow function should be executed across the federated edge clusters. We implement ClusterLess using OpenFaaS as the serverless execution substrate and Argo for workflow management, and deploy it on a realistic testbed of six edge clusters comprising 64 heterogeneous edge nodes. Experimental results with concurrent serverless workflows, spanning 18 workload configurations across different input sizes and deadline classes, show that ClusterLess reduces workflow completion time by up to 40 %, increases deadline satisfaction from below 50 % to over 90 %, and confines deadline violations to single digit seconds compared to four baseline methods.

cs.DC↗

arXiv2025

Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation

Data within a specific context gains deeper significance beyond its isolated interpretation. In distributed systems, interdependent data sources reveal hidden relationships and latent structures, representing valuable information for many applications. This paper introduces Osmotic Learning (OSM-L), a self-supervised distributed learning paradigm designed to uncover higher-level latent knowledge from distributed data. The core of OSM-L is osmosis, a process that synthesizes dense and compact representation by extracting contextual information, eliminating the need for raw data exchange between distributed entities. OSM-L iteratively aligns local data representations, enabling information diffusion and convergence into a dynamic equilibrium that captures contextual patterns. During training, it also identifies correlated data groups, functioning as a decentralized clustering mechanism. Experimental results confirm OSM-L's convergence and representation capabilities on structured datasets, achieving over 0.99 accuracy in local information alignment while preserving contextual integrity.

cs.LG↗

arXiv2025

Serverless Everywhere: A Comparative Analysis of WebAssembly Workflows Across Browser, Edge, and Cloud

WebAssembly (Wasm) is a binary instruction format that enables portable, sandboxed, and near-native execution across heterogeneous platforms, making it well-suited for serverless workflow execution on browsers, edge nodes, and cloud servers. However, its performance and stability depend heavily on factors such as startup overhead, runtime execution model (e.g., Ahead-of-Time (AOT) and Just-in-Time (JIT) compilation), and resource variability across deployment contexts. This paper evaluates a Wasm-based serverless workflow executed consistently from the browser to edge and cloud instances. The setup uses wasm32-wasi modules: in the browser, execution occurs within a web worker, while on Edge and Cloud, an HTTP shim streams frames to the Wasm runtime. We measure cold- and warm-start latency, per-step delays, workflow makespan, throughput, and CPU/memory utilization to capture the end-to-end behavior across environments. Results show that AOT compilation and instance warming substantially reduce startup latency. For workflows with small payloads, the browser achieves competitive performance owing to fully in-memory data exchanges. In contrast, as payloads grow, the workflow transitions into a compute- and memory-intensive phase where AOT execution on edge and cloud nodes distinctly surpasses browser performance.

cs.DC↗