Skip to main content
CVE-2026-114052VulnerabilityPublished Updated

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches

Affects vllmSource GCVE Database

0
Compare
Authoritative record:CVE-2026-114052· High 8.7

Not known to be exploited · CVSS 8.7 High : upgrade to 0.31.0 soon.

Data as of 4 Nov 2026, 11:17 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulnCheck)CVSS 4.08.7
CNA (VulnCheck)CVSS 3.17.5
Patch
Available – fixed in 0.31.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 21 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 4 Nov 2026.

What to do

Upgrade vllm to 0.31.0.

Affected software

ProductAffectedFixed in
PyPIvllmpkg:pypi/vllmOther threatsAffected
  • 0.24.0 – 0.30.0
  • >=0.24.0 <0.31.0
9 affected builds
Fixed in
  • 0.31.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade vLLM to version 0.31.0 or later, where this vulnerability is fixed. Since a patch is available, applying the official fix is the recommended mitigation. No other vendor advisory mitigation or workaround is indicated.

Description

vLLM versions after 0.24.0 and before 0.31.0 have a memory exhaustion vulnerability in the MOSS-Audio model serving component. This flaw arises because the system caches a processor for every distinct mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can exploit this by sending distinct or oversized mel_config values to the /tokenize endpoint, bypassing API key protections, leading to host memory exhaustion and crashing the API process. The vulnerability is fixed in version 0.31.0.

References

Community reviews

Loading reviews…