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 #624 from JustVugg/fix/622-metal-prefill-docs-debug-logits
Vincenzo Fornaro6fcc555652d0
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦