Comment by xnx 3 days ago Is this newer/better than the speculative decoding from 2022? https://arxiv.org/abs/2211.17192 2 comments xnx Reply tiahura 3 days ago Seems like they focus on improving the drafter and the verification policy so speculation keeps producing net speedups rather than wasted verification work at deepseek scale. alok-g 3 days ago That paper is cited in the 'introduction' and 'background' sections. This paper is improving by removing some bottlenecks.
tiahura 3 days ago Seems like they focus on improving the drafter and the verification policy so speculation keeps producing net speedups rather than wasted verification work at deepseek scale.
alok-g 3 days ago That paper is cited in the 'introduction' and 'background' sections. This paper is improving by removing some bottlenecks.
Seems like they focus on improving the drafter and the verification policy so speculation keeps producing net speedups rather than wasted verification work at deepseek scale.
That paper is cited in the 'introduction' and 'background' sections. This paper is improving by removing some bottlenecks.