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 #451 from ZacharyZcR/feat/cuda-grouped-g64
Vincenzo Fornaroe78fcfcbcaaf
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦