Chengying Huan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chengying Huan has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
- Chen Tian
Nanjing University, Nanjing, China
8 shared publications - Rong Gu
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
7 shared publications - Yongchao Liu
School of Geography and Remote Sensing, Ningbo University, Ningbo, China
7 shared publications - Zhibin Wang
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
7 shared publications - Guihai Chen
Shanghai Jiao Tong University
5 shared publications - Hang Liu
Rutgers, The State University of New Jersey, Piscataway, NJ, USA
5 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 458-473
SplineFS: Adaptive Learned Directory Indexing for Memory-Constrained Filesystems
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 458-473
Open AccessSplineFS: Adaptive Learned Directory Indexing for Memory-Constrained Filesystems
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8410-8417
GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8410-8417
Open AccessGraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
- Open Access
- 24 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (4) , 1-2
Corrigendum for CoDec: Prefix-Shared Decoding Kernel for LLMs
This is a corrigendum for the article ''CoDec: Prefix-Shared Decoding Kernel for LLMs'' published in Proc. ACM Manag. Data 4, 3 (SIGMOD), Article 151 (June 2026), 27 pages.
- 24 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (4) , 1-2
Open AccessCorrigendum for CoDec: Prefix-Shared Decoding Kernel for LLMs
This is a corrigendum for the article ''CoDec: Prefix-Shared Decoding Kernel for LLMs'' published in Proc. ACM Manag. Data 4, 3 (SIGMOD), Article 151 (June 2026), 27 pages.
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 125-138
STAR: Decode-Phase Rescheduling for LLM Inference
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 125-138
Open AccessSTAR: Decode-Phase Rescheduling for LLM Inference
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 249-264
BCCE: Block-Centric GPU Co-Design for Real-Time Range-Top-K Query at Scale
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 249-264
Open AccessBCCE: Block-Centric GPU Co-Design for Real-Time Range-Top-K Query at Scale
- Open Access
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
CoDec: Prefix-Shared Decoding Kernel for LLMs
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 co mbine the memory access of shared prefixes in the dec oding stage, namely CoDec. CoDec 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 CoDec achieves an average 1.9× speedup and 120.9× memory access reduction compared to the state-of-the-art FlashDecoding kernel regarding attention computation in the decode stage and 3.8× end-to-end time per output token compared to vLLM.
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
Open AccessCoDec: Prefix-Shared Decoding Kernel for LLMs
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 co mbine the memory access of shared prefixes in the dec oding stage, namely CoDec. CoDec 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 CoDec achieves an average 1.9× speedup and 120.9× memory access reduction compared to the state-of-the-art FlashDecoding kernel regarding attention computation in the decode stage and 3.8× end-to-end time per output token compared to vLLM.
- Open Access
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
CMANNS: GPU-Accelerated Graph Index Construction for ANNS via Compute–Memory Disaggregation
Graph-based approximate nearest neighbor search (ANNS) delivers state-of-the-art accuracy latency tradeoffs, yet index construction remains the bottleneck: fusing dense distance evaluation with irregular traversal or pruning collapses GPU throughput, and limited device memory forces costly data movement at scale. To address these problems, in this paper, we present CMANNS, a GPU-accelerated graph index construction framework that preserves the algorithmic rules of target graph (e.g., NSG and HNSW) and its query procedure. The core idea is compute–memory (CM) disaggregation : distance evaluation is reformulated as high–arithmetic-intensity GEMMs on Tensor Core accelerators with fused epilogues, while memory-intensive phases employ hot-set–aware on-chip locality (e.g., shared-memory staging, warp-cooperative gathers and scatters) to maximize effective bandwidth. To scale beyond the HBM capacity, we stream device-sized shards through a double-buffered pipeline and write back only compact adjacency. Data transfers and kernel execution overlap, so each shard completes in roughly the time of the slower step, keeping the GPU highly utilized even with irregular access. Across seven benchmarks, CMANNS reduces end-to-end index build time by up to 13.05x (vs. FAISS) and 2.20x (vs. FLASH), increases the cache hit rate by up to 58.7% , and preserves vector query latency and recall.
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
Open AccessCMANNS: GPU-Accelerated Graph Index Construction for ANNS via Compute–Memory Disaggregation
Graph-based approximate nearest neighbor search (ANNS) delivers state-of-the-art accuracy latency tradeoffs, yet index construction remains the bottleneck: fusing dense distance evaluation with irregular traversal or pruning collapses GPU throughput, and limited device memory forces costly data movement at scale. To address these problems, in this paper, we present CMANNS, a GPU-accelerated graph index construction framework that preserves the algorithmic rules of target graph (e.g., NSG and HNSW) and its query procedure. The core idea is compute–memory (CM) disaggregation : distance evaluation is reformulated as high–arithmetic-intensity GEMMs on Tensor Core accelerators with fused epilogues, while memory-intensive phases employ hot-set–aware on-chip locality (e.g., shared-memory staging, warp-cooperative gathers and scatters) to maximize effective bandwidth. To scale beyond the HBM capacity, we stream device-sized shards through a double-buffered pipeline and write back only compact adjacency. Data transfers and kernel execution overlap, so each shard completes in roughly the time of the slower step, keeping the GPU highly utilized even with irregular access. Across seven benchmarks, CMANNS reduces end-to-end index build time by up to 13.05x (vs. FAISS) and 2.20x (vs. FLASH), increases the cache hit rate by up to 58.7% , and preserves vector query latency and recall.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (6) , 1-30
Gem: Scalable Monotonic Graph Processing Beyond Billion-Scale on a Single Machine
Monotonic graph algorithms, such as shortest path, BFS, and reachability, are fundamental to graph analytics and are widely used across domains. Recent systems employ pruning techniques to accelerate the processing of these algorithms. However, state-of-the-art monotonic graph engines are restricted to in-memory execution and cannot scale to graphs that exceed main memory capacity. In contrast, existing out-of-core graph engines are designed for general-purpose workloads and lack effective pruning mechanisms tailored to monotonic graph algorithms. To bridge this gap, we present Gem, an out-of-core graph engine designed for monotonic graph algorithms. Gem introduces a PageRank-based graph sketch that captures key topological features inmemory with minimal preprocessing overhead. Building on this sketch, we propose a novel graph abstraction that enables the direct derivation of tight bounds for monotonic graph algorithms, supporting effective pruning at both the vertex and partition levels. Comprehensive evaluations on six real-world datasets, including the 42.5-billion-edge ClueWeb graph, show that Gem significantly outperforms existing systems. It achieves up to 135.40× speedup over GridGraph and 12.58× over Wonderland in out-of-core settings, and also delivers substantial improvements in other modes: up to 10.41× over RisGraph in memory and 20.64× over CGgraph out-of-GPU memory.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (6) , 1-30
Open AccessGem: Scalable Monotonic Graph Processing Beyond Billion-Scale on a Single Machine
Monotonic graph algorithms, such as shortest path, BFS, and reachability, are fundamental to graph analytics and are widely used across domains. Recent systems employ pruning techniques to accelerate the processing of these algorithms. However, state-of-the-art monotonic graph engines are restricted to in-memory execution and cannot scale to graphs that exceed main memory capacity. In contrast, existing out-of-core graph engines are designed for general-purpose workloads and lack effective pruning mechanisms tailored to monotonic graph algorithms. To bridge this gap, we present Gem, an out-of-core graph engine designed for monotonic graph algorithms. Gem introduces a PageRank-based graph sketch that captures key topological features inmemory with minimal preprocessing overhead. Building on this sketch, we propose a novel graph abstraction that enables the direct derivation of tight bounds for monotonic graph algorithms, supporting effective pruning at both the vertex and partition levels. Comprehensive evaluations on six real-world datasets, including the 42.5-billion-edge ClueWeb graph, show that Gem significantly outperforms existing systems. It achieves up to 135.40× speedup over GridGraph and 12.58× over Wonderland in out-of-core settings, and also delivers substantial improvements in other modes: up to 10.41× over RisGraph in memory and 20.64× over CGgraph out-of-GPU memory.
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (4) , 1-27
HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems
Prompt engineering techniques are widely used to enhance the generation quality of large language models (LLMs). However, the long prompts significantly increase inference latency and reduce inference throughput. Since many prompts share common prefixes, prefix sharing has been proposed to reuse shared prefix KV caches during inference. Nevertheless, the large number of prefix KV caches and the limited GPU memory capacity make it impractical to store all prefix KV caches in GPU memory. This limitation necessitates the use of external memory storage strategies, which often suffer from high I/O overhead and frequent cache misses with traditional approaches. To address these challenges, this paper proposes HotPrefix, a hotness-aware KV cache scheduling framework designed for efficient prefix sharing in LLM inference systems. HotPrefix introduces three core innovations: (1) Dynamic Hotness Tracking, which dynamically monitors and updates the hotness of prefix tree nodes over time; (2) Selective KV Cache Admission, which evaluates evicted KV caches from GPU memory, retaining only high-hotness caches in CPU memory to expand GPU memory capacity and reduce KV cache transfer overhead; (3) Hotness Promotion, which periodically promotes high-hotness prefix tree KV caches from CPU memory to GPU memory. This is combined with an efficient pipeline strategy for I/O and computation, ensuring GPU memory is allocated to the most critical prefixes while masking the I/O overhead associated with KV cache transmission. These mechanisms significantly improve cache hit rates, reduce inference latency, and enhance throughput. Implemented in the SGLang framework, HotPrefix reduces inference latency and increases throughput by up to 2.25× compared with vLLM with prefix sharing enabled. Against SGLang, it achieves up to 2× latency reduction and throughput increase.
- 22 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (4) , 1-27
Open AccessHotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems
Prompt engineering techniques are widely used to enhance the generation quality of large language models (LLMs). However, the long prompts significantly increase inference latency and reduce inference throughput. Since many prompts share common prefixes, prefix sharing has been proposed to reuse shared prefix KV caches during inference. Nevertheless, the large number of prefix KV caches and the limited GPU memory capacity make it impractical to store all prefix KV caches in GPU memory. This limitation necessitates the use of external memory storage strategies, which often suffer from high I/O overhead and frequent cache misses with traditional approaches. To address these challenges, this paper proposes HotPrefix, a hotness-aware KV cache scheduling framework designed for efficient prefix sharing in LLM inference systems. HotPrefix introduces three core innovations: (1) Dynamic Hotness Tracking, which dynamically monitors and updates the hotness of prefix tree nodes over time; (2) Selective KV Cache Admission, which evaluates evicted KV caches from GPU memory, retaining only high-hotness caches in CPU memory to expand GPU memory capacity and reduce KV cache transfer overhead; (3) Hotness Promotion, which periodically promotes high-hotness prefix tree KV caches from CPU memory to GPU memory. This is combined with an efficient pipeline strategy for I/O and computation, ensuring GPU memory is allocated to the most critical prefixes while masking the I/O overhead associated with KV cache transmission. These mechanisms significantly improve cache hit rates, reduce inference latency, and enhance throughput. Implemented in the SGLang framework, HotPrefix reduces inference latency and increases throughput by up to 2.25× compared with vLLM with prefix sharing enabled. Against SGLang, it achieves up to 2× latency reduction and throughput increase.
- Open Access
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (3) , 1-33
OTM : Efficient k -Order-Based Core Maintenance in Large-Scale Dynamic Hypergraphs
The k -core model has garnered widespread adoption for preserving essential cohesive subgraphs owing to its linear-time computability, making it particularly suitable for hypergraph analysis. However, considering the continuously evolving characteristics of real-world hypergraphs, recent research efforts have focused on developing efficient algorithms that can maintain the core value of each vertex amid structural alterations. Despite these efforts, frequent insertions and deletions in dynamic hypergraphs continue to pose significant inefficiencies, primarily due to the increased traversal overhead incurred by hyperedge insertion algorithms. This exacerbates performance disparities between handling hyperedge insertions and deletions, underscoring the persistent challenge of effective k -core analysis in hypergraphs. To effectively address these challenges, we have gained key insights that enable us to define a specific order, termed the hypergraph k -order, which significantly reduces redundant vertex traversal and narrows down the search space during hyperedge insertions. Based on the proposed hypergraph k -order, we define two indices, the order index and the pivotal index, aimed at minimizing traversal costs and expediting the hyperedge insertion algorithm. Moreover, it is essential to recognize that the recomputation of the support degree ( sd ) for all vertices following each hyperedge deletion can significantly diminish the performance efficiency of deletion algorithms. To address this, we introduce an optimized approach that leverages the incremental maintenance of the support degree ( sd ) value to expedite the hyperedge deletion process. By leveraging these optimizations, we introduce a novel Order-based Traversal core Maintenance methodology, designated as OTM , which markedly enhances the efficiency of core maintenance in dynamic hypergraphs. Our comprehensive evaluation, which covers 12 real-world hypergraph datasets and a synthetic dataset, reveals that OTM achieves staggering speedup, outperforming the state-of-the-art approach with a 41,420 \(\times\) speedup in the insertion algorithm and 8,284 \(\times\) speedup in the deletion algorithm, underscoring its remarkable efficiency and effectiveness.- 9 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (3) , 1-33
Open AccessOTM : Efficient k -Order-Based Core Maintenance in Large-Scale Dynamic Hypergraphs
The k -core model has garnered widespread adoption for preserving essential cohesive subgraphs owing to its linear-time computability, making it particularly suitable for hypergraph analysis. However, considering the continuously evolving characteristics of real-world hypergraphs, recent research efforts have focused on developing efficient algorithms that can maintain the core value of each vertex amid structural alterations. Despite these efforts, frequent insertions and deletions in dynamic hypergraphs continue to pose significant inefficiencies, primarily due to the increased traversal overhead incurred by hyperedge insertion algorithms. This exacerbates performance disparities between handling hyperedge insertions and deletions, underscoring the persistent challenge of effective k -core analysis in hypergraphs. To effectively address these challenges, we have gained key insights that enable us to define a specific order, termed the hypergraph k -order, which significantly reduces redundant vertex traversal and narrows down the search space during hyperedge insertions. Based on the proposed hypergraph k -order, we define two indices, the order index and the pivotal index, aimed at minimizing traversal costs and expediting the hyperedge insertion algorithm. Moreover, it is essential to recognize that the recomputation of the support degree ( sd ) for all vertices following each hyperedge deletion can significantly diminish the performance efficiency of deletion algorithms. To address this, we introduce an optimized approach that leverages the incremental maintenance of the support degree ( sd ) value to expedite the hyperedge deletion process. By leveraging these optimizations, we introduce a novel Order-based Traversal core Maintenance methodology, designated as OTM , which markedly enhances the efficiency of core maintenance in dynamic hypergraphs. Our comprehensive evaluation, which covers 12 real-world hypergraph datasets and a synthetic dataset, reveals that OTM achieves staggering speedup, outperforming the state-of-the-art approach with a 41,420 \(\times\) speedup in the insertion algorithm and 8,284 \(\times\) speedup in the deletion algorithm, underscoring its remarkable efficiency and effectiveness.