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 #444 from cdhdt/perf/idot-avxvnni-accumulators
Vincenzo Fornaro04ed0049a4b8
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦