Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia

PcChip | 2 hours ago

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

rancor | 2 hours ago

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

peddling-brink | an hour ago

> llama.cpp via Vulkan (AMD / Intel / NVIDIA) or CPU fallback

I got excited about someone paying attention to intel. Oh well.

dlcarrier | 59 minutes ago

From what I've seen, Vulkan adds a lot of overhead on Intel hardware.