LLMMedium
CVE-2026-34760: vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to befo…
- Occurred
- Apr 2, 2026
- Published
- Apr 2, 2026
- Source
- NVD CVE
Summary
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0.
Tags
- CVE
- CVE-2026-34760
- cvss:MEDIUM
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: CVE describes a technical discrepancy in audio processing within an LLM serving engine, causing inconsistency but no direct harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8