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 #651 from ZacharyZcR/feat/cuda-ans-expert-tier
Vincenzo Fornaroea24cb0a9ab5
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦