arXiv:2509.04719v3 Announce Type: replace-cross
Abstract: The widespread adoption of diffusion models for image generation necessitates efficient parallel inference to manage their substantial comput...
By Han Liang, Jiahui Zhou, Zicheng Zhou, Xiaoxi Zhang, Xu Chen
arXiv:2510. 01565v4 Announce Type: replace Abstract: Diffusion Transformer (DiT) models excel at generating high-quality images through iterative denoising steps, but serving them under strict Service Level Objectives (SLOs) is challenging due to their high computational cost, particularly at larger resolutions.
By Runyu Lu, Shiqi He, Wenxuan Tan, Shenggui Li, Ruofan Wu, Jeff J. Ma, Ang Chen, Mosharaf Chowdhury
EAServe introduces an encode-aware disaggregated serving framework for multimodal large language models (MLLMs), restructuring the traditional Prefill-Decode pipeline into a three-stage Encode-Prefill-Decode (EPD) system. By treating Encode as the control point, EAServe coordinates load‑adaptive micro‑batching, rate‑controlled offloading to prefill workers, and dynamic SM partitioning to balance GPU utilization across stages. Its Hybrid Auto Selection (HAS) layer optimizes GPU allocation, encode batch size, and offload ratio using capacity profiling and Bayesian optimization, achieving up to 4.3× higher goodput compared to NVIDIA Dynamo and 1.7× higher than vLLM on various MLLM architectures.
By Kunxiong Zhu, Zhihao Shu, Hangyu Zheng, Minghai Qin, Miao Yin, Gagan Agrawal, Wei Niu
arXiv:2606. 13501v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving.
By Xinwei Qiang, Yifan Hu, Shixuan Sun, Jing Yang, Han Zhao, Chen Chen, Yu Feng, Jingwen Leng, Minyi Guo
arXiv:2608. 12932v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control.
By Zekai Li, Yihao Liang, Hongfei Zhang, Jian Chen, Yesheng Liang, Zhijian Liu
Masked diffusion language models (dLLMs) promise faster text generation by denoising multiple tokens simultaneously, yet their real‑world serving behavior has been largely unexamined. Using LLaDA‑8B‑Instruct on a single NVIDIA H200 GPU, the study finds that request difficulty is discretized into 11 step‑count levels, short‑budget benchmarks underestimate serving variance, and only 24% of single‑request time is GPU computation, with batching mainly reducing CPU dispatch overhead. The authors also demonstrate that output quality remains stable across batch sizes and propose a batch‑timeout rule for synchronized batching under Poisson arrivals.
By Farhana Amin, Sabiha Afroz, Mona Moghadampanah, Dimitrios S. Nikolopoulos