2 papers
cs.CL2026
RouteSparse: Input-Conditional Pattern Routing for Budgeted Long-Context Prefilling
Chao Zhang, Yifan Ji, Ziyan Zhang +2
Dynamic sparse attention can reduce the quadratic cost of long-context prefilling without changing model weights. MInference assigns each attention head one pattern offline and est…
cs.DC2023
Hulk: Graph Neural Networks for Optimizing Regionally Distributed Computing Systems
Zhengqing Yuan, Huiwen Xue, Chao Zhang +1
Large deep learning models have shown great potential for delivering exceptional results in various applications. However, the training process can be incredibly challenging due to…