Strangely, I haven't had a lot of luck with vLLM; I finally ended up ditching Ol... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

fortyseven 5 months ago | parent | context | favorite | on: I ran Gemma 4 as a local model in Codex CLI

Strangely, I haven't had a lot of luck with vLLM; I finally ended up ditching Ollama and going straight to the tap with llama-serve in llamacpp. No regrets.

magic_hamster 5 months ago [–]

Good job. llama.cpp is already much better.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact