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

Join the discussion

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

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

  by peddling-brink
• From what I've seen, Vulkan adds a lot of overhead on Intel hardware.
  by dlcarrier
• I didn't see any benchmarks against vllm, sglang, exllama, etc
  by PcChip