1 matches found
PT-2026-152937
llama.cpp b11003 before b12556 contains an integer overflow in the hrm text loader load arch hparams that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load arch tensors to write tensor...
8.5CVSS6.5AI score0.00313EPSS
SaveExploits0References6
20