Runlong Su — accepted AI-conference papers

2025

Fast Video Generation with Sliding Tile Attention

Peiyuan Zhang, Yongqi Chen, Runlong Su, Hangliang Ding, Ion Stoica, Zhengzhong Liu +1

ICML 2025poster

Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video, attention alone takes 800 out of 950 seconds of total inference time. This paper introduces sliding tile attention (ST…

Cited by 5 Source ↗PDF ↗Scholar ↗

2024

Efficient LLM Scheduling by Learning to Rank

Yichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang

NeurIPS 2024poster

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and servic…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗