arXiv subjects

Tianyu Zuo

Publications and source records attributed to Tianyu Zuo.

5 recordsLinked to original sources

arXiv2026

Enabling High-Bandwidth Flash for Generative Recommendation Serving with Write-Aware KV Cache Policy

Generative recommendation (GR) systems increasingly leverage user-level KV cache reuse to avoid recomputing long user histories. However, the growing KV cache capacity and bandwidth requirements introduce new challenges for memory system. High-Bandwidth Flash (HBF) provides a promising solution by offering substantially higher capacity than HBM while approaching HBM-class read bandwidth, enabling larger scale KV cache retention and improved serving throughput. Yet conventional Least-Recently-Used (LRU) KV cache management tightly couples KV cache writes with cache misses, generating excessive write traffic that rapidly exhausts flash endurance. In this work, we evaluate a write-aware KV cache policy based on admission-controlled LRU-K for HBF-based GR serving. By filtering low-reuse users before cache admission, LRU-K decouples KV cache writes from misses and significantly reduces unnecessary writes. We develop an analytical model to characterize GR serving performance, KV cache write traffic, and HBF lifetime, and evaluate performance across diverse memory systems and GR workloads. Our results show that HBF-based systems achieve 3.8 to 4.7 times higher throughput than HBM-only systems. Moreover, LRU-K extends HBF lifetime from about one year under conventional LRU to over six years with a moderate K=10, while maintaining comparable or even slightly improved throughput. These results highlight the importance of write aware KV cache policy for sustainable HBF-based GR serving.

cs.AR↗

arXiv2025

On Competitiveness of Dynamic Replication for Distributed Data Access

This paper studies an online cost optimization problem for distributed storage and access. The goal is to dynamically create and delete copies of data objects over time at geo-distributed servers to serve access requests and minimize the total storage and network cost. We revisit a recent algorithm in the literature and show that it does not have a competitive ratio of $2$ as claimed by constructing a counterexample. We further prove that no deterministic online algorithm can achieve a competitive ratio bounded by $2$ for the general cost optimization problem. We develop an online algorithm and prove that it achieves a competitive ratio of $\max\{2, \min\{\gamma, 3\}\}$, where $\gamma$ is the max/min storage cost ratio among all servers. Examples are given to confirm the tightness of competitive analysis. We also empirically evaluate algorithms using real object access traces.

cs.DS↗

arXiv2025

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and further vulnerabilities. These pressures have produced two disjoint research lines: 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, versatility and efficiency have appeared fundamentally incompatible to co-achieve, with prior work consistently sacrificing one for the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information is concentrated in localized byte regions, motivating versatile yet efficient localized byte-sequence modeling rather than inefficient global modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing pipeline that directly embeds raw byte sequences. Crucially, to maintain versatility across diverse tasks, we propose a pattern-aware convolutional architecture equipped with dedicated scoring and gating mechanisms. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures. We prototype Nepco on the Nvidia BlueField-3 SmartNIC with multiengine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models, while reducing end-to-end latency by 328x to the millisecond scale.

cs.NI↗

arXiv2025

TraGe: A Generic Packet Representation for Traffic Classification Based on Header-Payload Differences

Traffic classification has a significant impact on maintaining the Quality of Service (QoS) of the network. Since traditional methods heavily rely on feature extraction and large scale labeled data, some recent pre-trained models manage to reduce the dependency by utilizing different pre-training tasks to train generic representations for network packets. However, existing pre-trained models typically adopt pre-training tasks developed for image or text data, which are not tailored to traffic data. As a result, the obtained traffic representations fail to fully reflect the information contained in the traffic, and may even disrupt the protocol information. To address this, we propose TraGe, a novel generic packet representation model for traffic classification. Based on the differences between the header and payload-the two fundamental components of a network packet-we perform differentiated pre-training according to the byte sequence variations (continuous in the header vs. discontinuous in the payload). A dynamic masking strategy is further introduced to prevent overfitting to fixed byte positions. Once the generic packet representation is obtained, TraGe can be finetuned for diverse traffic classification tasks using limited labeled data. Experimental results demonstrate that TraGe significantly outperforms state-of-the-art methods on two traffic classification tasks, with up to a 6.97% performance improvement. Moreover, TraGe exhibits superior robustness under parameter fluctuations and variations in sampling configurations.

cs.NI↗

arXiv2024

Cost-Driven Data Replication with Predictions

This paper studies an online replication problem for distributed data access. The goal is to dynamically create and delete data copies in a multi-server system as time passes to minimize the total storage and network cost of serving access requests. We study the problem in the emergent learning-augmented setting, assuming simple binary predictions about inter-request times at individual servers. We develop an online algorithm and prove that it is ($\frac{5+\alpha}{3}$)-consistent (competitiveness under perfect predictions) and ($1 + \frac{1}{\alpha}$)-robust (competitiveness under terrible predictions), where $\alpha \in (0, 1]$ is a hyper-parameter representing the level of distrust in the predictions. We also study the impact of mispredictions on the competitive ratio of the proposed algorithm and adapt it to achieve a bounded robustness while retaining its consistency. We further establish a lower bound of $\frac{3}{2}$ on the consistency of any deterministic learning-augmented algorithm. Experimental evaluations are carried out to evaluate our algorithms using real data access traces.

cs.DS↗