- CVSS
- MEDIUM · 6.5v3.1CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Published
- 2026-10-26
- Weakness
- CWE-770
- Source
- nvd.nist.gov/vuln/detail/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
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-115913 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.