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

Hu, T., Qin, J., Chen, L. et al. (10 more authors) (Accepted: 2026) FluidGPU: Fine-Grained Kernel Disaggregation for Large Model Inference on Heterogeneous GPUs. In: SC '26: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 15-20 Nov 2026, Chicago, IL, USA. ACM. (In Press)