llama.cpp
78e05298 - model : limite: reject mudd configs that index past mudd_tap_idx on load (#32562)

Commit
1 day ago
model : limite: reject mudd configs that index past mudd_tap_idx on load (#32562) n_mudd_taps comes from limite.mudd.tap_count, a scalar read separately from the length-checked tap_indices array. mudd_tap_idx is a fixed std::array<int32_t, 512> indexed at [i*n_taps] in both the tensor load and the graph build, so a crafted GGUF with n_layer * n_mudd_taps > 512 reads past the array. Reject that at hparams load; the one check covers both index sites.
Author
Parents
Loading