Hacker News new | ask | show | jobs
by reddguard 4 days ago
Doesn't Ollama use llama.cpp so their point stands even if they used it directly?
2 comments

No, because Ollama is buggy. The first step to answering GPC’s question is to try using an up to date llama.cpp.
It wouldn't be the first time ollama's llama.cpp fork reintroduced bugs and was missing important optimizations.
lol jealous hater
Huh?