AIConfPaper
← Search

YUAN WEN

2 accepted papers

2026

CONTINUUM: Restoring the Contiguous Tensor Abstraction Efficiently for Dynamic AI Workloads via Hardware Virtualization

Yangyu Zhang, shuoming zhang, Chunwei Xia, Shuaijiang Li, Zhicheng Li, Ruiyuan Xu +7
ICML 2026spotlight

Emerging LLM workloads demand extreme mem- ory agility. However, state-of-the-art inference systems (e.g., vLLM) rely on software-defined paging, which sacrifices the contiguous tensor abstraction. This rigid interface exposes fragmen- tation complexity to developers, imposing a se- vere engineering…

Cited by 0Source ↗Scholar ↗
2025

SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs

zhicheng li, Shuoming Zhang, Jiacheng Zhao, Siqi Li, Xiyu Shi, Yangyu Zhang +5
NeurIPS 2025poster

Recent multimodal large language models (MLLMs) marry modality-specific vision or audio encoders with a shared text decoder. While the encoder is compute- intensive but memory-light, the decoder is the opposite, yet state-of-the-art serving stacks still time-multiplex these complementary kernels, id…

Cited by 0Source ↗code ↗Scholar ↗