HN Explorer

KingJoker

↗ HN profile [ 41.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Low-latency local LLM runner via OpenJDK Panama FFM (Java 22) (github.com)

    I wanted to run AI from inside the JVM. I started out with the standard REST sidecar, ripped that out to use Project Panama (Foreign Function & Memory API) in the new JDK versions to interface directly with llama.cpp. I…

    3 points 10
  2. 1 points 1