alt Hacker NewsOllama is quite a bad example here. Despite popular, it's a simple wrapper and more and more pushed by the app it wraps llama.cpp.
Don't understand here the parallel.
Replies
eleventyseven • today at 8:47 AM
This is the vLLM of classic ML, not Ollama.
ekianjo • today at 6:11 AM
I guess the parallel is "Ollama serve" which provides you with a direct REST API to interact with a LLM.
➕ show 1 reply
TBVH I didn't think about naming it too much. I defaulted to Ollama because of the perceive simplicity and I wanted that same perceived simplicity to help adoption.