Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
AlphaUncommon

wici-ai/inferssd

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

Owner
wici-ai (organization)
Stars
Stars: 296
Forks
Forks: 44
Language
C++
License
Apache-2.0
Created
2026
Topics
apple-siliconcudaggufinferencellama-cppllmmetalmixture-of-expertsssd
Tier
Alpha (250 to 699 ★) What this tier means
View on GitHub

Nearby in C++

All C++ repos