collaborators

7 papers

cs.AR2026

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…

cs.AR2026

TOM: A Ternary Read-only Memory Accelerator for LLM-powered Edge Intelligence

Hongyi Guan, Yijia Zhang, Wenqiang Wang +4

The deployment of Large Language Models (LLMs) for real-time intelligence on edge devices is rapidly growing. However, conventional hardware architectures face a fundamental memory…

cs.AR2026

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…

cs.AI2026

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction

Chen Zhang, Kepu Zhang, Jiatong Zhang +2

Query correction is a critical entry point in modern search pipelines, demanding high accuracy strictly within real-time latency constraints. Chain-of-Thought (CoT) reasoning impro…

cs.DC2025

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…

cs.DC2025

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…