17 papers
Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
Yue Guan, Changming Yu, Shihan Fang +8
Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch betwe…
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…
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…
RapidStore: An Efficient Dynamic Graph Storage System for Concurrent Queries
Chiyu Hao, Jixian Su, Shixuan Sun +7
Dynamic graph storage systems are essential for real-time applications such as social networks and recommendation, where graph data continuously evolves. However, they face signifi…