PT-2026-125540

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama model loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash t...

PT-2024-40569

Name of the Vulnerable Software and Affected Versions: llama model loader affected versions not specified Description: The issue is related to a heap-buffer-overflow read error. Technical details indicate that the crash occurs in the gguf get tensor offset function, specifically within the llama...