Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
Merge pull request #535 from bherald/contrib/openai-stop-sequences
Vincenzo Fornaro11cd1c6456db
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦