Module inference 

CPU forward-pass primitives: RMS-norm, SiLU, sparse SwiGLU FFN.

Functions

rms_norm

RMS normalization with explicit weight semantics.

silu

SiLU activation function.

sparse_ffn_forward

Sparse SwiGLU FFN: compute only active_indices neurons.

sparse_ffn_forward_pair

Fused two-position sparse FFN: gate/up/down weight rows are streamed from memory ONCE for both positions. Bit-identical to two single calls (per-position accumulation order is unchanged).