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 #1396 from dmoraesrs/feat/web-reasoning-drop-medium-glm53
Vincenzo Fornaroba268dd328e6
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦