llama.cpp tokenizer signed vs. unsigned heap overflow
概要
llama.cpp tokenizer signed vs. unsigned heap overflow
原文の説明
取得元が公開している説明をそのまま載せています (多くは英語)。
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
出典: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
ディストリビューション別の修正状況
各ディストリビューションが公開している、この CVE の修正パッケージ
- Debian DEBIAN-CVE-2025-52566 llama.cpp 修正版: 5760+dfsg-1
- Ubuntu UBUNTU-CVE-2025-52566 llama.cpp
参照URL
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com