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 #1604 from Alfvenic/fix/glm53-vulkan-resident-guard-and-leak
Vincenzo Fornaro2f250262fc78
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦