CVE-2026-115913 — 脆弱性インテリジェンス
vllm — vllm
公表日:
- CVSS
- 6.5
- CISA KEV
- 未掲載（悪用がないことを意味しません）
情報源の原文（翻訳ではありません）
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.