nx_nn.nx

nx_nn.nx -- sovereign FIXED-POINT NEURAL INFERENCE substrate, the foundation under the neural-audio moonshot. The research established that neural audio is phone-CPU-viable BECAUSE it runs INT-quantised (DeepFilterNet RTF 0.04, Lyra 0.57ms/frame on a Pixel 6) -- not float, not GPU. So the sovereign path is integer matmul + bias + activation in a Q-scale, which is exactly what a learned PLC / RVQ-codebook net needs for its forward pass. This rung is the inference machinery (a linear layer + ReLU/tanh); the LEARNED weights come from the training pipeline (the next moonshot rung). Pure integer, no FPU, no syscalls -> phone-friendly + wasm-friendly. license_tier: ORIGINAL