gramrep

confirmedupstream bugC++Inference & servingJuly 13, 2026

the question

Is llama.cpp's GBNF bounded-repetition E{n,m} compiler safe when the bound is inverted (n greater than m)?

what came out

In handle_repetitions the loop count n_opt = max_times - min_times is a uint64 subtraction, so an inverted bound like {3,2} underflows to 2^64-1. The magnitude guard is keyed on max_times, not the loop count, so it never fires. {3,2}, {5,1}, {10,0} all fail to terminate: a compile-time DoS before any token is sampled.

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/gramrep