Skip to content

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 #1063 from terrizoaguimor/refactor/family-registry

Vincenzo Fornaro12368b7aa19f
diff --cc c/resource_plan.py
index ae8a62f3,ad70504e..8e7a324a
--- a/c/resource_plan.py
+++ b/c/resource_plan.py
@@@ -10,9 -10,11 +10,11 @@@ import subproces
import sys
from pathlib import Path
+ from family_registry import expert_contributions, planner_geometry, resolve_model
+
GB = 1_000_000_000
-EXPERT_RE = re.compile(r"model\.layers\.(\d+)\.mlp\.experts\.(\d+)\.")
+EXPERT_RE = re.compile(r"(?:model\.)?layers\.(\d+)\.(?:mlp|ffn)\.experts\.(\d+)\.")
def _tensor_sizes(path):