Chen Tian

Shushu Yi, Wenbo Wu, Guoci Chen et al.

GPU has become the leading computing device for a wide range of data-intensive applications, which tightly collaborates with remote all-flash array (AFA) to accommodate ever-expanding datasets, facilitate multi-client data sharing, and guarantee fault tolerance. Although GPU is the center of computation, all I/O processes in existing GPU-AFA systems are still CPU-centric. CPU orchestrates remote I/O requests and executes a centralized AFA engine to take charge of AFA-level functionalities (e.g., access control and metadata persistence). This design disparity suffers from substantial CPU-GPU interaction overhead and I/O traffic amplification, compromising end-to-end I/O performance. In this work, we present \emph{GNStor}, a GPU-native AFA system that enables GPU to directly access remote AFA without CPU intervention in the I/O path, thereby fully exploiting the performance of AFA. Specifically, GNStor first proposes a GPU-centric NVMe over RDMA (NoR) software stack (named \emph{GNoR}), paving a fast path for GPUs to directly initiate NoR I/O requests to SSDs within remote AFA. GNoR employs an atomic-operation-based I/O orchestration design and follows the single-instruction-multiple-thread (SIMT) execution model of GPU, fully exploiting the massive parallelism of GPU architectures. To facilitate essential AFA functionalities in a CPU-bypass I/O path, GNStor further designs \emph{deEngine}, a decentralized AFA engine that seamlessly decomposes and integrates AFA-level tasks into each SSD firmware, thereby achieving efficient AFA access at low cost. Evaluation results show that GNStor achieves 3.2$\times$ higher I/O throughput and reduces application execution time by 31.1\%, compared to state-of-the-art AFA systems.

Santosh Pandey, Zhibin Wang, Sheng Zhong et al.

Triangle counting is a building block for a wide range of graph applications. Traditional wisdom suggests that i) hashing is not suitable for triangle counting, ii) edge-centric triangle counting beats vertex-centric design, and iii) communication-free and workload balanced graph partitioning is a grand challenge for triangle counting. On the contrary, we advocate that i) hashing can help the key operations for scalable triangle counting on Graphics Processing Units (GPUs), i.e., list intersection and graph partitioning, ii)vertex-centric design reduces both hash table construction cost and memory consumption, which is limited on GPUs. In addition, iii) we exploit graph and workload collaborative, and hashing-based 2D partitioning to scale vertex-centric triangle counting over 1,000 GPUswith sustained scalability. In this work, we present TRUST which performs triangle counting with the hash operation and vertex-centric mechanism at the core. To the best of our knowledge, TRUSTis the first work that achieves over one trillion Traversed Edges Per Second (TEPS) rate for triangle counting.

Fuliang Liu, Xue Li, Ketai Zhao et al.

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accuracy at the cost of multi-step autoregressive inference, resulting in high drafting latency and ultimately rendering the drafting stage itself a performance bottleneck. Inspired by diffusion-based large language models (dLLMs), we propose DART, which leverages parallel generation to reduce drafting latency. DART predicts logits for multiple future masked positions in parallel within a single forward pass based on hidden states of the target model, thereby eliminating autoregressive rollouts in the draft model while preserving a lightweight design. Based on these parallel logit predictions, we further introduce an efficient tree pruning algorithm that constructs high-quality draft token trees with N-gram-enforced semantic continuity. DART substantially reduces draft-stage overhead while preserving high draft accuracy, leading to significantly improved end-to-end decoding speed. Experimental results demonstrate that DART achieves a 2.03x--3.44x wall-clock time speedup across multiple datasets, surpassing EAGLE3 by 30% on average and offering a practical speculative decoding framework. Code is released at https://github.com/fvliang/DART.

Xianpeng, Sun, Haonan Sun et al.

Evaluation of repository-aware software engineering systems is often confounded by synthetic task design, prompt leakage, and temporal contamination between repository knowledge and future code changes. We present a time-consistent benchmark methodology that snapshots a repository at time T0, constructs repository-derived code knowledge using only artifacts available before T0, and evaluates on engineering tasks derived from pull requests merged in the future interval (T0, T1]. Each historical pull request is transformed into a natural-language task through an LLM-assisted prompt-generation pipeline, and the benchmark is formalized as a matched A/B comparison in which the same software engineering agent is evaluated with and without repository-derived code knowledge while all other variables are held constant. We also report a baseline characterization study on two open-source repositories, DragonFly and React, using three Claude-family models and four prompt granularities. Across both repositories, file-level F1 increases monotonically from minimal to guided prompts, reaching 0.8081 on DragonFly and 0.8078 on React for the strongest tested model. These results show that prompt construction is a first-order benchmark variable. More broadly, the benchmark highlights that temporal consistency and prompt control are core validity requirements for repository-aware software engineering evaluation.

Yuhang Zhou, Zhibin Wang, Peng Jiang et al.

Training large language models faces frequent interruptions due to various faults, demanding robust fault-tolerance. Existing backup-free methods, such as redundant computation, dynamic parallelism, and data rerouting, each incur performance penalties, whether from ongoing overhead, lengthy reconfigurations, or post-recovery inefficiencies. We propose Chameleon, an adaptive fault-tolerant system that intelligently selects optimal recovery strategies when a failure occurs. Chameleon achieves this through a unified performance model, expedient execution plan search, accurate performance estimation, and efficient communication optimizations. Experiments on a 32-card cluster show that Chameleon maintains a performance gap of within 11.00% between post-recovery and failure-free training, while preserving model convergence and efficient memory usage. Compared to state-of-the-art methods, Chameleon achieves up to 1.229x and 1.355x higher average throughput than Oobleck and Recycle, respectively.

Chengying Huan, Ziheng Meng, Yongchao Liu et al.

Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT system co-designed with an optimized LLM serving architecture. GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption. To scale inference, we introduce a Graph-CoT-aware LLM inference mechanism with graph-specific KV-cache management, priority-based eviction, and pipelined execution to improve serving efficiency. Experiments demonstrate that GLM improves answer accuracy by up to 38%, reduces token cost by up to 95.7%, lowers inference latency by 90.3%, and achieves up to 15.1x higher throughput compared to state-of-the-art Graph-CoT baselines, enabling efficient adoption for complex real-world reasoning at scale.

Zhibin Wang, Shipeng Li, Yuhang Zhou et al.

User experience is a critical factor Large Language Model (LLM) serving systems must consider, where service level objectives (SLOs) considering the experience of individual requests and system level metrics (SLMs) considering the overall system performance are two key performance measures. However, we observe two notable issues in existing metrics: 1) manually delaying the delivery of some tokens can improve SLOs, and 2) actively abandoning requests that do not meet SLOs can improve SLMs, both of which are counterintuitive. In this paper, we revisit SLOs and SLMs in LLM serving, and propose a new SLO that aligns with user experience. Based on the SLO, we propose a comprehensive metric framework called smooth goodput, which integrates SLOs and SLMs to reflect the nature of user experience in LLM serving. Through this unified framework, we reassess the performance of different LLM serving systems under multiple workloads. Evaluation results show that our metric framework provides a more comprehensive view of token delivery and request processing, and effectively captures the optimal point of user experience and system performance with different serving strategies.

Zhibin Wang, Rui Ning, Chao Fang et al.

Prefix-sharing among multiple prompts presents opportunities to combine the operations of the shared prefix, while attention computation in the decode stage, which becomes a critical bottleneck with increasing context lengths, is a memory-intensive process requiring heavy memory access on the key-value (KV) cache of the prefixes. Therefore, in this paper, we explore the potential of prefix-sharing in the attention computation of the decode stage. However, the tree structure of the prefix-sharing mechanism presents significant challenges for attention computation in efficiently processing shared KV cache access patterns while managing complex dependencies and balancing irregular workloads. To address the above challenges, we propose a dedicated attention kernel to combine the memory access of shared prefixes in the decoding stage, namely FlashForge. FlashForge delivers two key innovations: a novel shared-prefix attention kernel that optimizes memory hierarchy and exploits both intra-block and inter-block parallelism, and a comprehensive workload balancing mechanism that efficiently estimates cost, divides tasks, and schedules execution. Experimental results show that FlashForge achieves an average 1.9x speedup and 120.9x memory access reduction compared to the state-of-the-art FlashDecoding kernel regarding attention computation in the decode stage and 3.8x end-to-end time per output token compared to the vLLM.

Zhibin Wang, Shipeng Li, Xue Li et al.

Large language models have been widely deployed in various applications, encompassing both interactive online tasks and batched offline tasks. Given the burstiness and latency sensitivity of online tasks, over-provisioning resources is common practice. This allows for the integration of latency-insensitive offline tasks during periods of low online load, enhancing resource utilization. However, strategically serving online and offline tasks through a preemption mechanism fails to fully leverage the flexibility of offline tasks and suffers from KV cache recomputation and irregular workloads. In this paper, we introduce Echo, a collaborative online-offline task serving system, including a scheduler, a KV cache manager, and estimation toolkits. The scheduler and KV cache manager work tightly to maximize the throughput of offline tasks, while the estimator further predicts execution time to ensure online task SLOs. The scheduler leverages the batch information of last iteration to reduce the search space for finding the optimal schedule. The KV cache manager sets the priority of the KV cache based on the type of tasks and the opportunity of prefix sharing to reduce the recomputation. Finally, the estimation toolkits predict the execution time, future memory consumption, and the throughput of offline tasks to guide the scheduler, KV cache manager, and the system deployer. Evaluation based on real-world workloads demonstrates that Echo can increase offline task throughput by up to $3.3\times$, while satisfying online task SLOs.

Zhibin Wang, Zetao Hong, Xue Li et al.

Large Language Model (LLM) inference has emerged as a fundamental paradigm. In real-world scenarios, variations in output length cause severe workload imbalance in the decode phase, particularly for long-output reasoning tasks. Existing systems, such as PD disaggregation architectures, rely on static prefill-to-decode scheduling, which often results in SLO violations and OOM failures under evolving decode workloads. In this paper, we propose ARES, an adaptive decoding rescheduling system powered by length prediction to anticipate future workloads. Our core contributions include: (1) A lightweight and continuous LLM-native prediction method that leverages LLM hidden state to model remaining generation length with high precision (reducing MAE by 49.42%) and low overhead (cutting predictor parameters by 93.28%); (2) A rescheduling solution in decode phase with : A dynamic balancing mechanism that integrates current and predicted workloads, reducing P99 TPOT by 74.77% and achieving up to 2.24 times higher goodput.

Hongxu Pan, Shuxian Hu, Mo Zhou et al.

Researchers have proposed various methods of incorporating more structured information into the design of Graph Neural Networks (GNNs) to enhance their expressiveness. However, these methods are either computationally expensive or lacking in provable expressiveness. In this paper, we observe that the chords increase the complexity of the graph structure while contributing little useful information in many cases. In contrast, chordless structures are more efficient and effective for representing the graph. Therefore, when leveraging the information of cycles, we choose to omit the chords. Accordingly, we propose a Chordless Structure-based Graph Neural Network (CSGNN) and prove that its expressiveness is strictly more powerful than the k-hop GNN (KPGNN) with polynomial complexity. Experimental results on real-world datasets demonstrate that CSGNN outperforms existing GNNs across various graph tasks while incurring lower computational costs and achieving better performance than the GNNs of 3-WL expressiveness.

Yujian Hu, Yilang Xiang, Yan-Jie Zhou et al.

The accurate and timely diagnosis of acute aortic syndromes (AAS) in patients presenting with acute chest pain remains a clinical challenge. Aortic CT angiography (CTA) is the imaging protocol of choice in patients with suspected AAS. However, due to economic and workflow constraints in China, the majority of suspected patients initially undergo non-contrast CT as the initial imaging testing, and CTA is reserved for those at higher risk. In this work, we present an artificial intelligence-based warning system, iAorta, using non-contrast CT for AAS identification in China, which demonstrates remarkably high accuracy and provides clinicians with interpretable warnings. iAorta was evaluated through a comprehensive step-wise study. In the multi-center retrospective study (n = 20,750), iAorta achieved a mean area under the receiver operating curve (AUC) of 0.958 (95% CI 0.950-0.967). In the large-scale real-world study (n = 137,525), iAorta demonstrated consistently high performance across various non-contrast CT protocols, achieving a sensitivity of 0.913-0.942 and a specificity of 0.991-0.993. In the prospective comparative study (n = 13,846), iAorta demonstrated the capability to significantly shorten the time to correct diagnostic pathway. For the prospective pilot deployment that we conducted, iAorta correctly identified 21 out of 22 patients with AAS among 15,584 consecutive patients presenting with acute chest pain and under non-contrast CT protocol in the emergency department (ED) and enabled the average diagnostic time of these 21 AAS positive patients to be 102.1 (75-133) mins. Last, the iAorta can help avoid delayed or missed diagnosis of AAS in settings where non-contrast CT remains the unavoidable the initial or only imaging test in resource-constrained regions and in patients who cannot or did not receive intravenous contrast.

Liu Yafeng, Chen Tian, Liu Zhongyu et al.

Human actions recognition has attracted more and more people's attention. Many technology have been developed to express human action's features, such as image, skeleton-based, and channel state information(CSI). Among them, on account of CSI's easy to be equipped and undemanding for light, and it has gained more and more attention in some special scene. However, the relationship between CSI signal and human actions is very complex, and some preliminary work must be done to make CSI features easy to understand for computer. Nowadays, many work departed CSI-based features' action dealing into two parts. One part is for features extraction and dimension reduce, and the other part is for time series problems. Some of them even omitted one of the two part work. Therefore, the accuracies of current recognition systems are far from satisfactory. In this paper, we propose a new deep learning based approach, i.e. C3D network and C3D network with attention mechanism, for human actions recognition using CSI signals. This kind of network can make feature extraction from spatial convolution and temporal convolution simultaneously, and through this network the two part of CSI-based human actions recognition mentioned above can be realized at the same time. The entire algorithm structure is simplified. The experimental results show that our proposed C3D network is able to achieve the best recognition performance for all activities when compared with some benchmark approaches.

Juanjuan Zhao, Fan Zhang, Lai Tu et al.

Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities. The understanding of passenger route choice is critical for public transit management. The wide deployment of Automated Fare Collection(AFC) systems opens up a new opportunity. However, only each trip's tap-in and tap-out timestamp and stations can be directly obtained from AFC system records; the train and route chosen by a passenger are unknown, which are necessary to solve our problem. While existing methods work well in some specific situations, they don't work for complicated situations. In this paper, we propose a solution that needs no additional equipment or human involvement than the AFC systems. We develop a probabilistic model that can estimate from empirical analysis how the passenger flows are dispatched to different routes and trains. We validate our approach using a large scale data set collected from the Shenzhen metro system. The measured results provide us with useful inputs when building the passenger path choice model.