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 #1153 from JustVugg/fix/web-reasoning-stream
Vincenzo Fornaroffd3eb7307ff
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦