Bing Lu

Bing Lu

Auto-generated profile, based on publicly available information

Bing Lu

Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

13 July 2026
Verified
Conference Paper
Open access
MLMan Liu
Man Liu
XLXingchen Liu
Xingchen Liu
XTXingjian Tian
Xingjian Tian
BLBing Lu
Bing Lu
SLShengkai Lyu
Shengkai Lyu
DTDingwen Tao
Dingwen Tao
Handling communication overhead in large-scale tensor-parallel training remains a critical challenge due to the dense, near-zero distributions of intermediate tensors, which exacerbate errors under frequent communication and introduce significant computational overhead during compression. To this end, we propose TACO (Tensor-parallel Adaptive COmmunication compression), a robust FP8-based framework for compressing TP intermediate tensors. First, we employ a data-driven reshaping strategy combined with an Adaptive Scale–Hadamard Transform to enable high-fidelity FP8 quantization, while its Dual-Scale Quantization mechanism ensures numerical stability throughout training. Second, we design a highly fused compression operator to reduce memory traffic and kernel launch overhead, allowing efficient overlap with communication. Finally, we integrate TACO with existing state-of-the-art methods for Data and Pipeline Parallelism to develop a compression-enabled 3D-parallel training framework. Detailed experiments on GPT models and Qwen model demonstrate up to 1.87 × end-to-end throughput improvement while maintaining near-lossless accuracy, validating the effectiveness and efficiency of TACO in large-scale training.

11 December 2025 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
XCXiang Chen
Xiang Chen
BLBing Lu
Bing Lu
HLHaoquan Long
Haoquan Long
HLHuizhang Luo
Huizhang Luo
YMYili Ma
Yili Ma
TLTao Lu
Tao Lu
Burst buffers (BBs) act as an intermediate storage layer between compute nodes and parallel file systems (PFS), effectively alleviating the I/O performance gap in high-performance computing (HPC). As scientific simulations and AI workloads generate larger checkpoints and analysis outputs, BB capacity shortages and PFS bandwidth bottlenecks are emerging, and CPU-based compression is not an effective solution due to its high overhead. We introduce Computational Burst Buffers (CBBs), a storage paradigm that embeds hardware compression engines such as application-specific integrated circuit (ASIC) inside computational storage drives (CSDs) at the BB tier. CBB transparently offloads both lossless and error-bounded lossy compression from CPUs to CSDs, thereby (i) expanding effective SSD-backed BB capacity, (ii) reducing BB–PFS traffic, and (iii) eliminating contention and energy overheads of CPU-based compression. Unlike prior CSD-based compression designs targeting databases or flash caching, CBB co-designs the burst-buffer layer and CSD hardware for HPC and quantitatively evaluates compression offload in BB–PFS hierarchies. We prototype CBB using a PCIe 5.0 CSD with an ASIC Zstd-like compressor and an FPGA prototype of an SZ entropy encoder, and evaluate CBB on a 16-node cluster. Experiments with four representative HPC applications and a large-scale workflow simulator show up to 61% lower application runtime, 8–12× higher cache hit ratios, and substantially reduced compute-node CPU utilization compared to software compression and conventional BBs. These results demonstrate that compression-aware BBs with CSDs provide a practical, scalable path to next-generation HPC storage.

1 June 2014
Verified
Conference Paper
Closed access
TGTeng Gang
Teng Gang
CBCuimei Bo
Cuimei Bo
LBLu Bing
Lu Bing
MSMa Shu
Ma Shu
Aiming at the complex operation and composition online detection problem of the industrial distillation, a multiple model soft sensing based on clustering arithmetic is proposed in the paper in order to realize the online soft sensor. Firstly, the principal component analysis and correlation analysis are used to preprocess a large amount of data set in order to acquire proper modeling sample set. And then, the K-means clustering method was used to analyze the modeling data, the multiple models are established using the partial least squares method. The proposed soft-sensing method was used to predict the composition of the product Butadiene. Practical applications indicated the proposed method was useful for the online prediction of the product quality.

11 August 2026
Verified
Conference Paper
Open access
ZLZedong Liu
Zedong Liu
XMXinyang Ma
Xinyang Ma
DLDejun Luo
Dejun Luo
HZHairui Zhao
Hairui Zhao
BLBing Lu
Bing Lu
GTGuangming Tan
Guangming Tan
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 bottle-neck. Existing KV compression are typically statically configured at runtime, 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 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 50x 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 9.13x JCT speedup in PD-separated serving and up to 32.8x TTFT reduction in KV-disaggregated serving.