CVE-2026-115913: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multim…
- Occurred
- Oct 26, 2026
- Published
- Oct 26, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-115913
- cvss:MEDIUM
Classification
Rationale: CVE describes a denial-of-service vulnerability in vLLM inference engine causing OOM via long audio input.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8