Story
arxiv_cs_lg · Nov 13, 2026 · paper
arxiv.orgNov 13, 2026
original source linked
In brief
Linear-attention language models replace a growing key-value cache with a recurrent state of fixed size. On an edge FPGA, this state can exceed the on-chip memory and must be paged to external memory. This paper asks whether such paging dominates the cost of decoding (generating