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 #1127 from view321/perf/iobench-subMB-blocks-and-per-thread-fd
Vincenzo Fornarode6fe7ef9156
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦