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

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

	▲	rancor 26 minutes ago \| parent [-]
		Since this is basically a wrapper around libllama.so, I would assume that the performance is roughly the same as llama.cpp upstream.