Kryptovaluta-ticker:
technology fra Arxiv cs.ai

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference

Cosmo Santoni, Anmol Thapar
Thursday at 04:00
3 Visninger
0 Kommentarer

arXiv:2603.09555v2 Announce Type: replace-cross Abstract: High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends. We show that the state space duality (SSD) recurrence has a compiler-friendly structure: diagonal per-head dynamics, fixed-size chunking, einsum-dominated...

Læs hele artiklen hos kilden.

Var dette nyttigt?
Del:

Kommentarer (0)

Vennligst logg inn for å skrive en kommentar

Ingen kommentarer ennå. Bli den første til å kommentere!