Existing large language model (LLM) serving systems typically batch the compute-bound prefill and I/O-bound decoding phases together.This co-location approach not only leads to significant interference between the two phases but also limits resource allocation and placements.To address these limitations, recent work proposes disaggregating the prefill and decoding phases to enhance performance.However, these works often rely on coarse-grained static scheduling strategies, resulting in imbalanced and insufficient resource utilization.For instance, compute resources for the prefill phase may be overloaded while those for the decoding phase remain idle, resulting in performance bottlenecks.In this paper, we propose WindServe, an efficient phase disaggregated LLM serving system that leverages stream-based, finegrained dynamic scheduling to enhance resource utilization and performance.WindServe features a global scheduler that monitors compute and memory resource usage to dynamically orchestrate cross-phase jobs, effectively reducing queuing delay and KV cache swapping overhead.We also introduce a stall-free rescheduling strategy to saturate the memory resources while minimizing the scheduling overhead from KV cache transfers.Furthermore, we design a stream-based approach to mitigate interference between prefill and decoding jobs.Our evaluation demonstrates that Wind-Serve achieves remarkable stability and SLO attainment under highload scenarios, outperforming state-of-the-art phase-disaggregated LLM serving systems by delivering a 4.28× improvement in TTFT median latency and a 1.5× reduction in TPOT P99 latency.

Graph Neural Networks (GNNs) have achieved significant success in anomaly detection across various domains. However, existing GNN approaches face notable challenges when applied to directed multigraphs where edge attributes serve as the sole source of information. This limitation complicates the learning of meaningful node representations and the accurate detection of anomalies, particularly in transaction networks. Moreover, existing methods typically suffer from dimensionality explosion and suboptimal use of structural and semantic information, leading to reduced detection performance. To address these challenges, we propose Feature Reconstruction for Anomaly Detection on Directed Multigraphs (FRAD-DM), a novel preprocessing framework tailored to enhance graph representations in node feature-absent scenarios. FRAD-DM employs advanced edge feature derivation techniques, temporal and structural subgraph analysis for node representation generation, and a reinforcement learning-based adaptive feature selection mechanism. This comprehensive framework optimizes feature spaces by balancing informativeness, task relevance, and computational efficiency, ensuring robust and scalable anomaly detection. Extensive experiments on real-world datasets under barely supervised settings demonstrate the effectiveness of FRAD-DM. By integrating it into various GNN architectures for node-level and edge-level anomaly detection tasks, negative-class F1-scores improve by 5.44% to 20.98%. These results highlight its capability to address the challenges of directed multigraphs in practical applications.