kvextremum

mixedupstream bugC++ · CPUInference & servingJuly 13, 2026

the question

Are llama.cpp's KV-cache seq_pos_min/max accessors exact, and does the documented contiguity guarantee hold under arbitrary sequence-op interleavings?

what came out

Mixed. A clean certificate was predicted; instead two defects surfaced over 48,024 exhaustive trials. seq_cp lacks a seq_has guard, so a repeated copy double-counts seq_pos and leaves seq_pos_max stale (returns 2 for an empty sequence). The documented [min,max] contiguity also fails after any interior seq_rm or partial seq_add/seq_div.

method & receipts

Result: mixed
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/kvextremum