papers

Publications (11)

cs.CV2025

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Tianchen Zhao, Ke Hong, Xinhao Yang +8

In visual generation, the quadratic complexity of attention mechanisms results in high memory and computational costs, especially for longer token sequences required in high-resolu…

cs.CV2025

MBQ: Modality-Balanced Quantization for Large Vision-Language Models

Shiyao Li, Yingchun Hu, Xuefei Ning +10

Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significa…

cs.CV2025

db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism

Siqi Chen, Ke Hong, Tianchen Zhao +4

Scaling Diffusion Transformer (DiT) inference via sequence parallelism is critical for reducing latency in visual generation, but is severely hampered by workload imbalance when ap…

cs.DC2025

Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering

Ke Hong, Xiuhong Li, Minxu Liu +9

Generative models have achieved remarkable success across various applications, driving the demand for multi-GPU computing. Inter-GPU communication becomes a bottleneck in multi-GP…

cs.CL2025

semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage

Ke Hong, Lufang Chen, Zhong Wang +9

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the u…

cs.DC2023

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs

Haotian Tang, Shang Yang, Zhijian Liu +6

Sparse convolution plays a pivotal role in emerging workloads, including point cloud processing in AR/VR, autonomous driving, and graph understanding in recommendation systems. Sin…

cs.LG2024

FlashDecoding++: Faster Large Language Model Inference on GPUs

Ke Hong, Guohao Dai, Jiaming Xu +6

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Sync…

cs.LG2025

TASP: Topology-aware Sequence Parallelism

Yida Wang, Ke Hong, Xiuhong Li +4

Long-context large language models (LLMs) face constraints due to the quadratic complexity of the self-attention mechanism. The mainstream sequence parallelism (SP) method, Ring At…

cs.CL2024

A Survey on Efficient Inference for Large Language Models

Zixuan Zhou, Xuefei Ning, Ke Hong +12

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirem…

cs.CV2023

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

Tianchen Zhao, Xuefei Ning, Ke Hong +8

Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a chall…

cs.AI2025

Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design

Zixiao Huang, Wen Zeng, Tianyu Fu +10

LLM-based search agents achieve strong performance but suffer from severe latency, as each step requires serialized LLM reasoning followed by action of tool execution. We revisit t…