CVE-2025-71439

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama vocab::impl::print info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id to token and crash.