Expand description
Host-side 0.40B-shaped (or tiny) K3 weights for the C1 CPU graph.
Structs§
- Ablation
- Graph mutants. Mix=0 / force-expert-0 are C1; skip-layer is C2;
o_projTP is C7. - Dense
Mlp - K3Cpu
Layer - K3Cpu
Model - CPU twin (or tiny stand-in) ready for greedy decode.
- KdaWeights
- MlaWeights
- MoeWeights