Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
Unofficial Hacker News client; not affiliated with Y Combinator.
colinsane · · focus · HN ↗
so this is just a go binary that exec's `llama-server --model $MODEL_PATH ...`? there's room for llama wrappers, sure, but the readme only shows features that are already exposed directly from llama-server. it doesn't seem to do anything besides rename the CLI arguments: i don't get it.