Viewing profile — KingJoker
KingJoker
HN member- Joined
- Tue, Mar 24, 2015, 1:42 AM UTC
- HN karma
- 18
- Public activity
- 8 items
- HN profile
- View on Hacker News ↗
About KingJoker
No profile information was provided.
Recent public activity
-
comment
Comment #48950758
Glad to hear! Let me know if you run into any issues!
-
comment
Comment #48933132
You're welcome, I appreciate the engagement! Your intuitions are right, faster switching between agent calls, and tighter packing of agents in the same amount of compute space. The…
-
comment
Comment #48930112
I addressed this a little bit in the comment below, but the cycles add up. I'm doing some pretty crazy things higher up in the stack, that I'm not quite ready to release yet. But e…
-
comment
Comment #48930072
To start with, it eliminates the IPC and Sidecar overhead of using something like Ollama. It might seem trivial when comparing the speed of a REST request to that of inferencing, b…
-
comment
Comment #48908149
Thanks! It was a fun challenge getting an AI agent to pair with me while adhering to strict c-struct padding and memory alignment. Let me know if anything sticks out you'd like to …
-
story
Show HN: Low-latency local LLM runner via OpenJDK Panama FFM (Java 22)
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 …
- comment
- story