Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia (github.com)

20 points by Maverick617 an hour ago

2 comments:

by PcChip 40 minutes ago

I didn't see any benchmarks against vllm, sglang, exllama, etc

by rancor 31 minutes ago

Since this is basically a wrapper around libllama.so, I would assume that the performance is roughly the same as llama.cpp upstream.

Data from: Hacker News, provided by Hacker News (unofficial) API