pith. machine review for the scientific record. sign in

ArXiv , year=

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

1 Pith paper citing it

fields

cs.LG 1

years

2022 1

verdicts

ACCEPT 1

representative citing papers

Fast Inference from Transformers via Speculative Decoding

cs.LG · 2022-11-30 · accept · novelty 7.0

Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.

citing papers explorer

Showing 1 of 1 citing paper.

  • Fast Inference from Transformers via Speculative Decoding cs.LG · 2022-11-30 · accept · none · ref 28

    Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.