wici-ai/inferssd: run models larger than RAM or VRAM by streaming MoE experts from SSD; built on llama.cpp
Read the original at github.com→★ 75 stars
Original headline: "wici-ai/inferssd: Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp."
Coverage timeline
- Oct 22, 10:40 UTC GitHub Trending (AI) lead source wici-ai/inferssd: Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.