CVE-2026-115913

NameCVE-2026-115913
DescriptionvLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py uses eager attention by default, allowing a remote client to submit one legal long audio clip that causes MultiHeadedAttention.forward_attention to materialize and retain full attention matrices in self.attn. The scaled dot-product attention branch does not materialize these matrices. The resulting quadratic GPU-memory use can cause an out-of-memory condition and terminate EngineCore for all users. This issue is fixed in version 0.32.0.
SourceCVE (at NVD; CERT, ENISA, LWN, oss-sec, fulldisc, Debian ELTS, Red Hat, Ubuntu, Gentoo, SUSE bugzilla/CVE, GitHub advisories/code/issues, web search, more)
Debian Bugs1095237

The information below is based on the following data on fixed versions.

PackageTypeReleaseFixed VersionUrgencyOriginDebian Bugs
vllmITP1095237

Search for package or bug name: Reporting problems