collaborators

6 papers

cs.CL2026

SpecLA: Efficient Speculative Decoding for Linear-Attention Models

Zhibin Wang, Xuying Han, Zhaohua Yang +5

Linear-attention models replace the growing KV cache with recurrent states, but autoregressive decoding still reads, updates, and writes these states one token at a time. Speculati…

cs.DC2026

STAR: Decode-Phase Rescheduling for LLM Inference

Zhibin Wang, Zetao Hong, Xue Li +8

Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalance in the decode phase, particularly f…

cs.LG2026

CoDec: Prefix-Shared Decoding Kernel for LLMs

Zhibin Wang, Rui Ning, Chao Fang +12

Prefix-sharing among multiple prompts presents opportunities to combine the operations of the shared prefix, while attention computation in the decode stage, which becomes a critic…

cs.CL2026

DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference

Fuliang Liu, Xue Li, Ketai Zhao +7

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accur…

cs.LG2025

Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving

Zhibin Wang, Shipeng Li, Yuhang Zhou +7

User experience is a critical factor Large Language Model (LLM) serving systems must consider, where service level objectives (SLOs) considering the experience of individual reques…

cs.DC2025

Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving

Zhibin Wang, Shipeng Li, Xue Li +7

Large language models have been widely deployed in various applications, encompassing both interactive online tasks and batched offline tasks. Given the burstiness and latency sens…