Preprint
Jul 2026
HEMERA: A Heterogeneous Memory-Centric Accelerator with Recursive Dataflow for Edge-Constrained State-Space-Duality Models Inference
HEMERA is presented, a heterogeneous memory-centric accelerator for efficient Mamba-2 inference that reformulates the matrix-form SSD computation into an algebraically equivalent streaming-recursive dataflow that avoids quadratic intermediate storage while preserving the original computation.
Hao Ding, Ling Liang, Ruitong Qiao et al.
· 0 citations