Publications (11)
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…