‹ BackHN Continuity

Thread

Faster prompt lookup drafting in llama.cpp

89 points · 12 comments · pptadversary

  1. jadidbourbaki · · focus · HN ↗
    As an update to this, Lemire absolutely crushed it! I benchmarked his change today. Here is my PR comment:

    <a href="https:&#x2F;&#x2F;github.com&#x2F;jadidbourbaki&#x2F;llama.cpp&#x2F;pull&#x2F;12#issuecomment-5856228676" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;jadidbourbaki&#x2F;llama.cpp&#x2F;pull&#x2F;12#issuecomm...

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.