arXiv subjects

Wenyuan Yu

Publications and source records attributed to Wenyuan Yu.

At least 19 recordsLinked to original sources

arXiv2026

SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans. This shifts the workload in two ways: (1) agents act only on complete responses, making the cluster's tokens per second (TPS) the primary goal and relaxing--not eliminating--per-token latency requirements; and (2) requests share much of their KV\$-reuse exceeds 80% of request tokens in a production trace from BAILIAN, versus 54-62% in chat. This paper first contributes a systematic study of request scheduling for agents on two real-world traces. We find that to increase KV\$ reuse, existing schedulers overly prioritize routing requests to instances caching their KV\$, overloading a few while leaving the rest idle, capping TPS. We thus present two key insights: (1) load balance need not sacrifice all KV\$ reuse, thanks to the global-tier KV\$ store and (2) by utilizing the workload's intra-session locality, balancing a small fraction of requests--the first request in each agent session--suffices to balance the cluster without sacrificing most KV\$ reuse on local instances. SMETRIC realizes these insights with balanced session-centric scheduling: it routes each session's first request purely for load balance and its follow-up requests in a cache-aware manner, preserving load balance and local reuse while keeping demand on the global tier low. Using the session turn information as the scheduling metric is deliberate: it is derived efficiently and accurately from the user inputs alone, so the scheduler stays clean and stateless. SMETRIC improves cluster TPS by 10-16% under prefill-decode colocation with a global store and prefill TPS by 2-34% under disaggregation over state-of-the-art schedulers, also with a better per-token latency.

cs.DC↗

arXiv2026

Wan-Image: Pushing the Boundaries of Generative Visual Intelligence

We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at aesthetic generation, they frequently encounter critical bottlenecks in rigorous design workflows that demand absolute controllability, complex typography rendering, and strict identity preservation. To address these challenges, Wan-Image features a natively unified multi-modal architecture by synergizing the cognitive capabilities of large language models with the high-fidelity pixel synthesis of diffusion transformers, which seamlessly translates highly nuanced user intents into precise visual outputs. It is fundamentally powered by large-scale multi-modal data scaling, a systematic fine-grained annotation engine, and curated reinforcement learning data to surpass basic instruction following and unlock expert-level professional capabilities. These include ultra-long complex text rendering, hyper-diverse portrait generation, palette-guided generation, multi-subject identity preservation, coherent sequential visual generation, precise multi-modal interactive editing, native alpha-channel generation, and high-efficiency 4K synthesis. Across diverse human evaluations, Wan-Image exceeds Seedream 5.0 Lite and GPT Image 1.5 in overall performance, reaching parity with Nano Banana Pro in challenging tasks. Ultimately, Wan-Image revolutionizes visual content creation across e-commerce, entertainment, education, and personal productivity, redefining the boundaries of professional visual synthesis.

cs.CV↗

arXiv2026

Simple is Better: Multiplication May Be All You Need for LLM Request Scheduling

High-quality LLM request scheduling requires meeting two key objectives: ensuring the routed instance has KVCache to accelerate request execution, and ensuring that the workload is balanced across instances. Achieving both objectives is challenging because pursuing one may compromise the other. Current approaches use various combinators (e.g., linear combinations) to compute a scheduling score that combines indicators for the two objectives. These approaches are complex: they either require significant workload-specific hyperparameter tuning or model-hardware-aware simulator development, yet could still lead to suboptimal performance. In this paper, we show that using a simple multiplication of two carefully chosen indicators: one KVCache-aware (new prefill tokens if routed to an instance) and one load-balancing-aware (current batch size of the instance), as the scheduling score (LMETRIC) can achieve both objectives simultaneously without any hyperparameter tuning. The key idea is that the simply multiplied score considers both objectives in a manner similar to a linear combination, but the original hyperparameters cancel out during comparison, so no tuning is needed to find the best parameters. The two indicators are chosen based on our analysis of LLM characteristics. Our extensive experiments show that this simple approach can reduce TTFT by 92% and 39%, and TPOT by 24% and 51%, compared to vLLM-v1 and an in-production scheduler on real-world workloads covering chatbots and coding agents. We also derive the mathematical conditions under which multiplication may fail, and find that such conditions are extremely rare in practice and can be detected (and mitigated) beforehand. LMETRIC has been deployed in production and canary release confirms its effectiveness

cs.DC↗

arXiv2026

A Hypergraph-Based Framework for Exploratory Business Intelligence

Business Intelligence (BI) analysis is evolving towards Exploratory BI, an iterative, multi-round exploration paradigm where analysts progressively refine their understanding. However, traditional BI systems impose critical limits for Exploratory BI: heavy reliance on expert knowledge, high computational costs, static schemas, and lack of reusability. We present ExBI, a novel system that introduces the hypergraph data model with operators, including Source, Join, and View, to enable dynamic schema evolution and materialized view reuse. Using sampling-based algorithms with provable estimation guarantees, ExBI addresses the computational bottlenecks, while maintaining analytical accuracy. Experiments on LDBC datasets demonstrate that ExBI achieves significant speedups over existing systems: on average 16.21x (up to 146.25x) compared to Neo4j and 46.67x (up to 230.53x) compared to MySQL, while maintaining high accuracy with an average error rate of only 0.27% for COUNT, enabling efficient and accurate large-scale exploratory BI workflows.

cs.DB↗

arXiv2026

Efficient Vector Search in the Wild: One Model for Multi-K Queries

Learned top-K search is a promising approach for serving vector queries with both high accuracy and performance. However, current models trained for a specific K value fail to generalize to real-world multi-K queries: they suffer from accuracy degradation (for larger Ks) and performance loss (for smaller Ks). Training the model to generalize on different Ks requires orders of magnitude more preprocessing time and is not suitable for serving vector queries in the wild. We present OMEGA, a K-generalizable learned top-K search method that simultaneously achieves high accuracy, high performance, and low preprocessing cost for multi-K vector queries. The key idea is that a base model properly trained on K=1 with our trajectory-based features can be used to accurately predict larger Ks with a dynamic refinement procedure and smaller Ks with minimal performance loss. To make our refinements efficient, we further leverage the statistical properties of top-K searches to reduce excessive model invocations. Extensive evaluations on multiple public and production datasets show that, under the same preprocessing budgets, OMEGA achieves 6-33% lower average latency compared to state-of-the-art learned search methods, while all systems achieve the same recall target. With only 16-30% of the preprocessing time, OMEGA attains 1.01-1.28x of the optimal average latency of these baselines.

cs.DB↗

arXiv2025

Qwen3Guard Technical Report

As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in static evaluation settings, face two major limitations in real-world applications: (1) they typically output only binary "safe/unsafe" labels, which can be interpreted inconsistently across diverse safety policies, rendering them incapable of accommodating varying safety tolerances across domains; and (2) they require complete model outputs before performing safety checks, making them fundamentally incompatible with streaming LLM inference, thereby preventing timely intervention during generation and increasing exposure to harmful partial outputs. To address these challenges, we present Qwen3Guard, a series of multilingual safety guardrail models with two specialized variants: Generative Qwen3Guard, which casts safety classification as an instruction-following task to enable fine-grained tri-class judgments (safe, controversial, unsafe); and Stream Qwen3Guard, which introduces a token-level classification head for real-time safety monitoring during incremental text generation. Both variants are available in three sizes (0.6B, 4B, and 8B parameters) and support up to 119 languages and dialects, providing comprehensive, scalable, and low-latency safety moderation for global LLM deployments. Evaluated across English, Chinese, and multilingual benchmarks, Qwen3Guard achieves state-of-the-art performance in both prompt and response safety classification. All models are released under the Apache 2.0 license for public use.

cs.CL↗

arXiv2025

Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration

Efficient video generation models are increasingly vital for multimedia synthetic content generation. Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality video generation. However, their multi-step iterative denoising process incurs high computational cost and inference latency. Caching, a widely adopted optimization method in DiT models, leverages the redundancy in the diffusion process to skip computations in different granularities (e.g., step, cfg, block). Nevertheless, existing caching methods are limited to single-granularity strategies, struggling to balance generation quality and inference speed in a flexible manner. In this work, we propose MixCache, a training-free caching-based framework for efficient video DiT inference. It first distinguishes the interference and boundary between different caching strategies, and then introduces a context-aware cache triggering strategy to determine when caching should be enabled, along with an adaptive hybrid cache decision strategy for dynamically selecting the optimal caching granularity. Extensive experiments on diverse models demonstrate that, MixCache can significantly accelerate video generation (e.g., 1.94$\times$ speedup on Wan 14B, 1.97$\times$ speedup on HunyuanVideo) while delivering both superior generation quality and inference efficiency compared to baseline methods.

cs.GR↗

arXiv2025

KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially improves serving throughput and latency. However, there is limited understanding of how LLM serving benefits from KV\$ caching, where system design decisions like cache eviction policies are highly workload-dependent. In this paper, we present the first systematic characterization of the KV\$ workload patterns from one of the leading LLM service providers. We draw observations that were not covered by previous studies focusing on synthetic workloads, including: KV\$ reuses are skewed across requests, where reuses between single-turn requests are equally important as multi-turn requests; the reuse time and probability are diverse considering all requests, but for a specific request category, the pattern tends to be predictable; and the overall cache size required for an ideal cache hit ratio is moderate. Based on the characterization, we further propose a workload-aware cache eviction policy that improves the serving performance under real-world traces, especially with limited cache capacity.

cs.DC↗

arXiv2025

OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source Software

Usability evaluation is critical to the impact and adoption of open source software (OSS), yet traditional methods relying on human evaluators suffer from high costs and limited scalability. To address these limitations, we introduce OSS-UAgent, an automated, configurable, and interactive agent-based usability evaluation framework specifically designed for open source software. Our framework employs intelligent agents powered by large language models (LLMs) to simulate developers performing programming tasks across various experience levels (from Junior to Expert). By dynamically constructing platform-specific knowledge bases, OSS-UAgent ensures accurate and context-aware code generation. The generated code is automatically evaluated across multiple dimensions, including compliance, correctness, and readability, providing a comprehensive measure of the software's usability. Additionally, our demonstration showcases OSS-UAgent's practical application in evaluating graph analytics platforms, highlighting its effectiveness in automating usability evaluation.

cs.SE↗

arXiv2025

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation

Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video generation remains computationally intensive, especially for high-resolution, long-duration videos. Prior work accelerates its inference by skipping computation, usually at the cost of severe quality degradation. In this paper, we propose SRDiffusion, a novel framework that leverages collaboration between large and small models to reduce inference cost. The large model handles high-noise steps to ensure semantic and motion fidelity (Sketching), while the smaller model refines visual details in low-noise steps (Rendering). Experimental results demonstrate that our method outperforms existing approaches, over 3$\times$ speedup for Wan with nearly no quality loss for VBench, and 2$\times$ speedup for CogVideoX. Our method is introduced as a new direction orthogonal to existing acceleration strategies, offering a practical solution for scalable video generation.

cs.GR↗

arXiv2025

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production

With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process: they are critical for motivating and benchmarking serving techniques and systems. However, the existing understanding of real-world LLM serving workloads is limited due to the lack of a comprehensive workload characterization. Prior analyses remain insufficient in scale and scope, thus failing to fully capture intricate workload characteristics. In this paper, we fill the gap with an in-depth characterization of LLM serving workloads collected from our worldwide cloud inference serving service, covering not only language models but also emerging multimodal and reasoning models, and unveiling important new findings in each case. Moreover, based on our findings, we propose ServeGen, a principled framework for generating realistic LLM serving workloads by composing them on a per-client basis. A practical use case in production validates that ServeGen avoids 50% under-provisioning compared to naive workload generation, demonstrating ServeGen's advantage in performance benchmarking. ServeGen is available at https://github.com/alibaba/ServeGen.

cs.DC↗

arXiv2025

A Graph-native Optimization Framework for Complex Graph Queries

This technical report extends the SIGMOD 2025 paper "A Modular Graph-Native Query Optimization Framework" by providing a comprehensive exposition of GOpt's advanced technical mechanisms, implementation strategies, and extended evaluations. While the original paper introduced GOpt's unified intermediate representation (GIR) and demonstrated its performance benefits, this report delves into the framework's implementation depth: (1) the full specification of GOpt's optimization rules; (2) a systematic treatment of semantic variations (e.g., homomorphism vs. edge-distinct matching) across query languages and their implications for optimization; (3) the design of GOpt's Physical integration interface, enabling seamless integration with transactional (Neo4j) and distributed (GraphScope) backends via engine-specific operator customization; and (4) a detailed analysis of plan transformations for LDBC benchmark queries.

cs.DB↗

arXiv2025

Wan: Open and Advanced Large-Scale Video Generative Models

This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1.

cs.CV↗

arXiv2025

Revisiting Graph Analytics Benchmark

The rise of graph analytics platforms has led to the development of various benchmarks for evaluating and comparing platform performance. However, existing benchmarks often fall short of fully assessing performance due to limitations in core algorithm selection, data generation processes (and the corresponding synthetic datasets), as well as the neglect of API usability evaluation. To address these shortcomings, we propose a novel graph analytics benchmark. First, we select eight core algorithms by extensively reviewing both academic and industrial settings. Second, we design an efficient and flexible data generator and produce eight new synthetic datasets as the default datasets for our benchmark. Lastly, we introduce a multi-level large language model (LLM)-based framework for API usability evaluation-the first of its kind in graph analytics benchmarks. We conduct comprehensive experimental evaluations on existing platforms (GraphX, PowerGraph, Flash, Grape, Pregel+, Ligra and G-thinker). The experimental results demonstrate the superiority of our proposed benchmark.

cs.DB↗

arXiv2025

Influence of the Deformation of Coronal Mass Ejections on Their In-Situ Fitting with Circular-Cross-Section Flux Rope Models

Understanding the properties, especially the magnetohydrodynamic (MHD) invariants, of coronal mass ejections (CMEs) measured in-situ is key to bridging the CME properties from the Sun to interplanetary space. In order to investigate CMEs from the in-situ measurements that provide a one-dimensional (1-D) cut of the CME parameters over the spacecraft trajectory, various magnetic flux rope (MFR) models have been developed, among which the models with a circular cross-section are the most popular and widely used. CMEs are found to be deformed during their propagation in interplanetary space, in which the cross-section may be flattened in the direction of propagation, i.e., to develop an elliptical or even pancake-like shape. We use numerical MHD simulations in 2.5-D to investigate the influence of the CME deformation on the in-situ fitting using two linear force-free MFR models with a circular cross-section, and we focus on the axial and poloidal magnetic fluxes, which are conserved in the ideal MHD frame and simulations. We quantitatively compare the fitted axial and poloidal fluxes with those in simulations. We find that both models underestimate the axial flux compared to that in simulations, and such underestimation depends on the CME deformation. However, the fitting of the poloidal flux is independent of the deformation. We discuss the reasons for the axial flux underestimation and the implication of the CME deformation for the CME in-situ fitting.

physics.space-ph↗

arXiv2025

Static Batching of Irregular Workloads on GPUs: Framework and Application to Efficient MoE Model Inference

It has long been a problem to arrange and execute irregular workloads on massively parallel devices. We propose a general framework for statically batching irregular workloads into a single kernel with a runtime task mapping mechanism on GPUs. We further apply this framework to Mixture-of-Experts (MoE) model inference and implement an optimized and efficient CUDA kernel. Our MoE kernel achieves up to 91% of the peak Tensor Core throughput on NVIDIA H800 GPU and 95% on NVIDIA H20 GPU.

cs.DC↗

arXiv2025

Qwen2.5-1M Technical Report

We introduce Qwen2.5-1M, a series of models that extend the context length to 1 million tokens. Compared to the previous 128K version, the Qwen2.5-1M series have significantly enhanced long-context capabilities through long-context pre-training and post-training. Key techniques such as long data synthesis, progressive pre-training, and multi-stage supervised fine-tuning are employed to effectively enhance long-context performance while reducing training costs. To promote the use of long-context models among a broader user base, we present and open-source our inference framework. This framework includes a length extrapolation method that can expand the model context lengths by at least four times, or even more, without additional training. To reduce inference costs, we implement a sparse attention method along with chunked prefill optimization for deployment scenarios and a sparsity refinement method to improve precision. Additionally, we detail our optimizations in the inference engine, including kernel optimization, pipeline parallelism, and scheduling optimization, which significantly enhance overall inference performance. By leveraging our inference framework, the Qwen2.5-1M models achieve a remarkable 3x to 7x prefill speedup in scenarios with 1 million tokens of context. This framework provides an efficient and powerful solution for developing applications that require long-context processing using open-source models. The Qwen2.5-1M series currently includes the open-source models Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, as well as the API-accessed model Qwen2.5-Turbo. Evaluations show that Qwen2.5-1M models have been greatly improved in long-context tasks without compromising performance in short-context scenarios. Specifically, the Qwen2.5-14B-Instruct-1M model significantly outperforms GPT-4o-mini in long-context tasks and supports contexts eight times longer.

cs.CL↗

arXiv2024

Exact Acceleration of Subgraph Graph Neural Networks by Eliminating Computation Redundancy

Graph neural networks (GNNs) have become a prevalent framework for graph tasks. Many recent studies have proposed the use of graph convolution methods over the numerous subgraphs of each graph, a concept known as subgraph graph neural networks (subgraph GNNs), to enhance GNNs' ability to distinguish non-isomorphic graphs. To maximize the expressiveness, subgraph GNNs often require each subgraph to have equal size to the original graph. Despite their impressive performance, subgraph GNNs face challenges due to the vast number and large size of subgraphs which lead to a surge in training data, resulting in both storage and computational inefficiencies. In response to this problem, this paper introduces Ego-Nets-Fit-All (ENFA), a model that uniformly takes the smaller ego nets as subgraphs, thereby providing greater storage and computational efficiency, while at the same time guarantees identical outputs to the original subgraph GNNs even taking the whole graph as subgraphs. The key is to identify and eliminate the redundant computation among subgraphs. For example, a node $v_i$ may appear in multiple subgraphs but is far away from all of their centers (the unsymmetric part between subgraphs). Therefore, its first few rounds of message passing within each subgraph can be computed once in the original graph instead of being computed multiple times within each subgraph. Such strategy enables our ENFA to accelerate subgraph GNNs in an exact way, unlike previous sampling approaches that often lose the performance. Extensive experiments across various datasets reveal that compared with the conventional subgraph GNNs, ENFA can reduce storage space by 29.0% to 84.5% and improve training efficiency by up to 1.66x.

cs.AI↗