monoexp

confirmedcertificateC · Apple M4Inference & servingJuly 12, 2026

the question

Is llama.cpp's NEON ggml_v_expf monotone non-decreasing over its fp32 softmax domain?

what came out

Zero strict inversions over all 2,239,853,076 adjacent fp32 pairs in [-104, 88.72], despite the kernel's 1.45-ulp inaccuracy. It is exactly monotone non-decreasing, so softmax is rank-preserving and no smaller logit can overtake a larger one. The pre-registered prediction of reduction-seam inversions was falsified.

method & receipts

Result: confirmed
Pre-registered — the prediction was written down and committed before the run.
Reproducible — one script re-runs the whole thing from scratch.
Tested — a correctness/benchmark suite ships alongside the code.

→ read the code and re-run it

github.com/v-code01/monoexp