arXiv subjects

Zedong Liu

Publications and source records attributed to Zedong Liu.

8 recordsLinked to original sources

arXiv2026

Tools-CC-Bench: a Benchmark Suite for Collective Communication with Compression in HPC and AI Workloads

Distributed HPC and LLM workloads increasingly require efficient communication for scalability, yet growing data movement has become a major performance bottleneck. Communication compression can reduce this overhead and complement execution-level optimizations, but its benefits remain difficult to assess because existing benchmarks lack support for diverse backends, realistic datasets, application-specific accuracy metrics, and overlap-induced resource contention. We present CC-Bench, a lightweight, extensible, and application-oriented benchmark suite for evaluating communication compression under realistic execution conditions. CC-Bench uses declarative application-environment modeling to decouple profiling logic from communication libraries, datasets, and fidelity metrics, enabling portable cross-library evaluation. It further combines function-level interception and hardware counter monitoring to characterize per-phase latency, hardware utilization, numerical fidelity, and computation interference. With representative datasets from HPC and LLM workloads, CC-Bench evaluates three compression-enabled communication libraries on CPU and GPU clusters, revealing accuracy-performance trade-offs and bottlenecks to guide practical deployment and optimization.

cs.DC↗

arXiv2026

Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents

Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute task-relevant evidence, while existing context-reduction methods mainly intervene after broad content has already entered the trajectory. We present SparseRead, a training-free, model-transparent reading layer that controls content admission before unnecessary evidence reaches the model context. SparseRead combines a regime-aware Read Gate, extensible Reader Backends, and a stateful protocol for bounded, source-anchored evidence acquisition with explicit refinement, verification, stopping, and fallback. Across six frontier models, including Claude Opus 5, and five workload scenarios, SparseRead reduces token volume by up to 92.9% and wall time by up to 89.0%, while preserving or improving task quality. Its consistent gains across three agent frameworks further demonstrate broad portability.

cs.AI↗

arXiv2026

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression are typically static runtime configurations, despite production service context varies over time in workload mix, bandwidth, and SLO/quality budgets. As a result, a fixed choice can be suboptimal or even increase latency. We present \emph{KVServe}, the first service-aware and adaptive KV communication compression framework for disaggregated LLM serving: KVServe (1) unifies KV compression into a modular strategy space with new components and cross-method recomposition; (2) introduces Bayesian Profiling Engine that efficiently searches this space and distills a 3D Pareto candidate set, reducing $50\times$ offline search overhead; and (3) deploys a Service-Aware Online Controller that combines an analytical latency model with a lightweight bandit to select profiles under constraints and correct offline-to-online mismatch. Integrated into vLLM and evaluated across datasets, models, GPUs and networks, KVServe achieves up to $9.13\times$ JCT speedup in PD-separated serving and up to $32.8\times$ TTFT reduction in KV-disaggregated serving.

cs.DC↗

arXiv2026

CCL-D: A High-Precision Diagnostic System for Slow and Hang Anomalies in Large-Scale Model Training

As training scales grow, collective communication libraries (CCL) increasingly face anomalies arising from complex interactions among hardware, software, and environmental factors. These anomalies typically manifest as slow/hang communication, the most frequent and time-consuming category to diagnose. However, traditional diagnostic methods remain inaccurate and inefficient, frequently requiring hours or even days for root cause analysis. To address this, we propose CCL-D, a high-precision diagnostic system designed to detect and locate slow/hang anomalies in large-scale distributed training. CCL-D integrates a rank-level real-time probe with an intelligent decision analyzer. The probe measures cross-layer anomaly metrics using a lightweight distributed tracing framework to monitor communication traffic. The analyzer performs automated anomaly detection and root-cause location, precisely identifying the faulty GPU rank. Deployed on a 4,000-GPU cluster over one year, CCL-D achieved near-complete coverage of known slow/hang anomalies and pinpointed affected ranks within 6 minutes-substantially outperforming existing solutions.

cs.DC↗

arXiv2026

SJET: An Interactive Solar Jet Extraction Tool

Solar jets are dynamic collimated plasma flows in the solar atmosphere that play crucial roles in coronal heating and solar wind acceleration. Their complex and diverse morphologies pose significant challenges for developing universal algorithms for automatic identification and extraction, particularly for on-disk jets affected by projection effects and background contamination. We present SJET, an interactive tool for solar jet feature extraction using multiple algorithms developed in Python that integrates five thresholding algorithms with morphological operations. SJET implements a novel method for identifying start and end points based on circular regions that objectively determines jet propagation direction by exploiting morphological asymmetry, combined with modeling the axis using quadratic B\'ezier curves for accurate extraction of geometric parameters including length, width, curvature, and deflection angles. Validation analyses using Solar Orbiter/EUI high-resolution image and SDO/AIA observations demonstrate SJET's effectiveness across different observational conditions, with good agreement compared to traditional analysis methods, though the tool's accuracy remains dependent on user-defined threshold parameters and region of interest selection. SJET provides a solution to method inconsistency in solar jet research through standardized processing workflows, establishing a technical foundation for large-sample statistical studies.

astro-ph.SR↗

arXiv2026

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs

The rapid scaling of Large Language Models presents significant challenges for their deployment and inference, particularly on resource-constrained specialized AI hardware accelerators such as Huawei's Ascend NPUs, where weight data transfer has become a critical performance bottleneck. While lossless compression can preserve model accuracy and reduce data volume, existing lossless compression algorithms exhibit extremely low throughput when ported to the Ascend NPU architecture. In this paper, we propose ENEC, a novel lossless compression method specifically customized for AI model weights and optimized for Ascend Neural Processing Units. ENEC adopts a block-based fixed-length encoding scheme and incorporates a series of NPU-specific optimizations: bit-width quantization with hierarchical halving bit-packing, vectorized branch-free integer transformation, and dependency-decoupled intra-segment scan for efficient prefix-sum computation. Experimental results demonstrate that ENEC outperforms existing state-of-the-art NPU compressors in both compression ratio and throughput. Compared to leading GPU solutions, ENEC achieves a 3.43X higher throughput than DietGPU and a 1.12X better compression ratio than nvCOMP. By reducing weight transmission overhead, ENEC significantly improves end-to-end inference performance, achieving up to a 6.3X speedup. On Ascend NPUs, ENEC is the first open-source lossless compression algorithm for model weights that achieves performance comparable to state-of-the-art GPU compressors, offering an effective solution for deploying large-scale AI models.

cs.AR↗

arXiv2025

ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and heterogeneous workloads -- introduce significant inference overhead. Therefore, efficiently serving MLLMs remains a major challenge. Current tightly coupled serving architectures struggle to distinguish between mixed request types or adapt parallelism strategies to different inference stages, leading to increased time-to-first-token (TTFT) latency and poor resource utilization. To address this, we introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity across request types and inference stages. Building upon EMP, we develop ElasticMM, an MLLM serving system that (1) separates requests into independent modality groups with dynamic resource allocation via a modality-aware load balancer; (2) decouples inference stages and enables parallelism adjustment and adaptive scaling via elastic partition scheduling; and (3) improves inference efficiency through unified multimodal prefix caching and non-blocking encoding. Experiments on diverse real-world datasets show that ElasticMM outperforms state-of-the-art (SOTA) serving systems, reducing TTFT by up to 4.2x and achieving 3.2-4.5x higher throughput while meeting service-level objectives (SLOs).

cs.DC↗

arXiv2025

SolarZip: An Efficient and Adaptive Compression Framework for Solar EUV Imaging Data

Context: With the advancement of solar physics research, next-generation solar space missions and ground-based telescopes face significant challenges in efficiently transmitting and/or storing large-scale observational data. Aims: We develop an efficient compression and evaluation framework for solar EUV data, specifically optimized for Solar Orbiter Extreme Ultraviolet Imager (EUI) data, significantly reducing data volume while preserving scientific usability. Methods: We systematically evaluated four error-bounded lossy compressors across two EUI datasets. However, the existing methods cannot perfectly handle the EUI datasets (with continuously changing distance and significant resolution differences). Motivated by this, we develop an adaptive hybrid compression strategy with optimized interpolation predictors. Moreover, we designed a two-stage evaluation framework integrating distortion analysis with downstream scientific workflows, ensuring that observational analysis is not affected at high compression ratios. Results: Our framework SolarZip achieved up to 800x reduction for Full Sun Imager (FSI) data and 500x for High Resolution Imager (HRI$_{\text{EUV}}$) data. It significantly outperformed both traditional and advanced algorithms, achieving 3-50x higher compression ratios than traditional algorithms, surpassing the second-best algorithm by up to 30%. Simulation experiments verified that SolarZip can reduce data transmission time by up to 270x while ensuring the preservation of scientific usability. Conclusions: The SolarZip framework significantly enhances solar observational data compression efficiency while preserving scientific usability by dynamically selecting optimal compression methods based on observational scenarios and user requirements. This provides a promising data management solution for deep space missions like Solar Orbiter.

astro-ph.IM↗