FluidGPU: Fine-Grained Kernel Disaggregation for Large Model Inference on Heterogeneous GPUs

Tiancheng Hu, Jin Qin, Lei Chen, Junhao Hu, Yuzheng Wang, Zheng Wang, Yizhou Shan, Mingxing Zhang, Ting Cao, Chunwei Xia, Huimin Cui, Chenxi Wang, Tao Xie

Type

Conference paper

Publication

The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026)

Date

July, 2026

Links

Preprint