5 papers
AoiZora: Topology-Aware Auto-Parallel Optimization for Inference of Diffusion Transformers
Kaijian Wang, Yuanyuan Xu, Fanjiang Ye +5
Video diffusion has quickly grown into a key generative serving workload, yet producing each clip demands many denoising iterations over large spatio-temporal latents, which puts l…
Characterization-Guided GPU Fault Resilience in NVIDIA MPS
Rixin Liu, Xingqi Cui, Kaijian Wang +4
NVIDIA Multi-Process Service (MPS) enables fine-grained GPU sharing by allowing multiple processes to execute concurrently on the same GPU, making it an important mechanism for imp…
ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads
Jingwei Zuo, Xinze Feng, Zien Liu +5
Low-Rank Adaptation (LoRA) is now the dominant method for parameter-efficient fine-tuning of large language models, but achieving a high-quality adapter often requires systematic h…
GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads
Fanjiang Ye, Zhangke Li, Xinrui Zhong +10
Diffusion models have emerged as the prevailing approach for text-to-image (T2I) and text-to-video (T2V) generation, yet production platforms must increasingly serve both modalitie…
SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling
Fanjiang Ye, Zepeng Zhao, Yi Mu +11
Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is r…