pith. sign in

Transformers are rnns: Fast autoregressive transformers with linear attention

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

KVBuffer: IO-aware Serving for Linear Attention

cs.LG · 2026-05-18 · unverdicted · novelty 7.0

KVBuffer reduces linear attention decoding latency by up to 45% and increases speculative decoding throughput 5x by buffering keys/values for flexible chunked and parallel computation.

citing papers explorer

Showing 1 of 1 citing paper.

  • KVBuffer: IO-aware Serving for Linear Attention cs.LG · 2026-05-18 · unverdicted · none · ref 6

    KVBuffer reduces linear attention decoding latency by up to 45% and increases speculative decoding throughput 5x by buffering keys/values for flexible chunked and parallel computation.