CVE-2026-115913

Description

vLLM 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.

References

• https://github.com/vllm-project/vllm/commit/3d52578e13454de0bb8352cac988347cdcc89928
• https://github.com/vllm-project/vllm/pull/60614
• https://github.com/vllm-project/vllm/releases/tag/v0.32.0
• https://github.com/vllm-project/vllm/security/advisories/GHSA-8397-8qf6-f2gm