ZeroDay Findings
Sign inSign up

Findings

CVE-2026-34760

vLLM is an inference and serving engine for large language models (LLMs).

Published Apr 2, 2026 · updated Jul 24, 2026 · vllm vllm

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.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Apr 2, 2026 · NIST NVD

    Detected

    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 au

  2. Jul 24, 2026 · NIST NVD

    Updated

    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 au

Affected

  • cpe vllm/vllmversion unspecified

Sources

  • CVE.orgVulnerability recordCVE-2026-34760

    Official CVE identifier

    cve.org
  • NIST NVDVulnerability recordCVE-2026-34760

    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. Th

    nvd.nist.gov

References