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

github.com - 34 poäng - 4 kommentarer - 8357 sekunder sedan

Kommentarer (3)

peddling-brink - 1032 sekunder sedan
> llama.cpp via Vulkan (AMD / Intel / NVIDIA) or CPU fallback
I got excited about someone paying attention to intel. Oh well.
dlcarrier - 955 sekunder sedan
From what I've seen, Vulkan adds a lot of overhead on Intel hardware.
PcChip - 5808 sekunder sedan
I didn't see any benchmarks against vllm, sglang, exllama, etc