JustVugg

Headlines · 1

1. Nov 3
   Colibri v2.1.0 Brings Tiered MoE Inference to Local Hardware

   JustVugg released colibri v2.1.0, an open-source C inference engine that places frequently used MoE experts on CUDA or Vulkan GPUs, keeps warm experts in RAM, and streams cold experts from NVMe. The project says the engine can run large open models on existing hardware without requiring a GPU and currently provides 13 engines, including 10 for language models.

   GitHub Trending（每日） · 🔥 0

Experience and discussion from the community

Share my JustVugg experienceAsk about JustVugg