Thread

Self-hosted inference orchestrators compared: LocalAI, exo, GPUStack, vLLM

13 points · 7 comments · nextime

polotics · 1789934927 · focus · HN ↗
what exactly did you mean when xou wrote this paragraph title: "LiteLLM — a router, not a runtime' ?
1. nextime · 1789975475 · focus · HN ↗
  I wouldn't wrote as it, sorry, the post was an unintended generated post, wasn't supposed to post for real, until i was going to rewrite it by hand at least.
  The meaning for that sentence is that litellm just route requests, it doesn't execute a model.

Unofficial Hacker News client; not affiliated with Y Combinator.