w1n5t0n f225c7c2a6 feat(wasm): add batch inference, extended training, pin mask, eval loss, and layer stats bindings ...

Five new C functions for the WASM module:
- nisps_mlp_infer_batch: N-point batch inference in a single call
- nisps_mlp_train_ex: training with per-iteration loss history output
- nisps_mlp_move_weights_ex: moveWeights with output pin mask to skip pinned nodes
- nisps_mlp_eval_loss: compute MSE loss without updating weights
- nisps_mlp_get_layer_stats: per-layer weight magnitude, dead, and saturation stats

2026-04-03 17:11:49 +01:00

36 KiB

Executable file

Raw History

View raw