Mend.io Vulnerability Database
The largest open source vulnerability database
What is a Vulnerability ID?
New vulnerability? Tell us about it!
CVE-2026-34760
Published:April 02, 2026
Updated:May 15, 2026
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.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.8.3 <0.18.0
Fix Suggestion:
Update to version 0.18.0
https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.5.5 <v0.18.0
Fix Suggestion:
Update to version v0.18.0
vllm (PYTHON):
Affected version(s) >=0.5.5 <0.18.0
Fix Suggestion:
Update to version 0.18.0
Do you need more information?
Contact Us
CVSS v4
Base Score:
6
Attack Vector
NETWORK
Attack Complexity
HIGH
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
HIGH
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
5.9
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
HIGH
Availability
LOW
Weakness Type (CWE)
Improper Input Validation
EPSS
Base Score:
0.07