11 citations · 16 across the 32 of their papers we have counts for
35 papers
From Overloaded to Guaranteed: High-Throughput Multi-SLO Enforcement for LoRA-Assisted On-Premise LLM Deployment
Zeshen Zhang, Han Zhao, Weihao Cui +9
As Large Language Models (LLMs) become essential in privacy-sensitive sectors like hospitals and government agencies, the on-premise LLM servers offer a cost-effective and secure a…
ByteSplat: Efficient Distributed 3D Gaussian Splatting Training via Intra- and Inter-GPU communication reduction
Shuo Wu, He Zhu, Han Zhao +9
3D Gaussian Splatting (3DGS) enables photorealistic scene reconstruction, but training large-scale scenes requires substantial memory and computation. Distributing training across…
Atlas: Algorithm-Hardware Co-Design for On-Device City-Scale 3D Gaussian Splatting in VR
He Zhu, Zheng Liu, Xingyang Li +8
3D Gaussian splatting (3DGS) has drawn significant attention in the architectural community recently. However, enabling city scale 3DGS on mobile VR devices remains challenging, as…
A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation
Zihan Liu, Jingwen Leng, Yangjie Zhou +12
Modern GPUs increasingly integrate Tensor Cores into the execution pipeline. Although aggregate tensor throughput continues to grow, aided by an operand supply that has evolved fro…
Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference
Zheng Liu, Zeyu Guo, Zihan Liu +9
Vision-language-action (VLA) models have emerged as a key component in embodied AI. Among existing approaches, diffusion-based VLA models achieve superior motion quality and genera…
DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization
Minnan Pei, Gang Li, Zeyu Zhu +7
3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time novel view synthesis, yet existing 3DGS accelerators suffer from poor architectural scalability: incre…
DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction
Chi Zhang, Jieru Zhao, Yu Feng +3
Diffusion Transformers (DiTs) have been widely used in many tasks, including image synthesis, video generation, and content editing. However, their multi-iteration inference proces…
Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations
Wenxuan Miao, Haosong Liu, Weiming Hu +9
Video diffusion transformers (vDiTs) generate high quality video but introduce extremely high compute cost due to the long diffusion timesteps and self attention computation. As di…
GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design
Yitong Ding, Jiawei Huang, Renyang Guan +7
Modern LLM (large language model) workloads increasingly rely on optimized GPU kernels through hardware-software co-design. These kernels achieve high-performance through fine-grai…
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
Xinwei Qiang, Yifan Hu, Shixuan Sun +6
Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each…
ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing
Kang You, Chen Nie, Lee Jun Yan +6
Spiking neural networks (SNNs) exploit event-driven and addition-only computation to substantially improve efficiency for intelligent computation. A key temporal property of SNNs,…
Mosaic: Towards Efficient Training of Multimodal Models with Spatial Resource Multiplexing
Yanbo Wang, Yuxuan Wang, Chen Chen +6
With the wide adoption of Multimodal Models (MMs) in real-world scenarios, it is significant to efficiently train emerging MMs that exhibit increasingly complex module architecture…
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
Zhengyi Li, Yakai Wang, Kang Yang +6
For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client's input. However,…
M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization
Weiming Hu, Zihan Zhang, Haoyan Zhang +8
Existing low-bit Microscaling (MX) formats, such as MXFP4, often suffer from substantial accuracy degradation due to the use of a shared scaling factor with the Power-of-Two format…
FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
Ziyu Huang, Yangjie Zhou, Zihan Liu +8
The scaling of computation throughput continues to outpace improvements in memory bandwidth, making many deep learning workloads memory-bound. Kernel fusion is a key technique to a…
Splatonic: Architecture Support for 3D Gaussian Splatting SLAM via Sparse Processing
Xiaotong Huang, He Zhu, Tianrui Ma +8
3D Gaussian splatting (3DGS) has emerged as a promising direction for SLAM due to its high-fidelity reconstruction and rapid convergence. However, 3DGS-SLAM algorithms remain impra…
Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
Wenxuan Miao, Yulin Sun, Aiyue Chen +7
The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly bas…
Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
Mingyan Yang, Guanjie Wang, Manqi Luo +6
LLM agents, which often comprise parallel inference tasks, are commonly adopted to solve real-world problems. When serving such task-parallel LLM agents in shared GPU servers, the…
SpikingBrain: Spiking Brain-inspired Large Models
Yuqi Pan, Yupeng Feng, Jinghao Zhuang +16
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows lin…
ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
Xinhao Luo, Zihan Liu, Yangjie Zhou +8
Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. Th…
SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity
Xingyang Li, Jie Jiang, Yu Feng +5
Rendering is critical in fields like 3D modeling, AR/VR, and autonomous driving, where high-quality, real-time output is essential. Point-based neural rendering (PBNR) offers a pho…
STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
Chenqi Zhang, Yu Feng, Jieru Zhao +4
3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 fram…
Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
Yu Feng, Weikai Lin, Yuge Cheng +6
3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propos…
Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers
Haosong Liu, Yuge Cheng, Wenxuan Miao +8
Video diffusion transformers (vDiTs) have made tremendous progress in text-to-video generation, but their high compute demands pose a major challenge for practical deployment. Whil…