---
id: CVE-2026-114052
title: >-
  vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize
  mm_processor_kwargs
summary: >-
  vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability
  in MOSS-Audio model serving that caches a processor for every distinct
  request-controlled mm_processor_kwargs value in an unbounded dictionary.
  Unauthenticate…
severity: high
cvss: 7.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'
cvssSource: cna
cwe:
  - CWE-770
vendor: vllm-project
product: vllm
affected:
  - vllm >= 0.25.0 < 0.31.0
published: '2026-10-21'
updated: '2026-10-21'
sourceUpdated: '2026-10-21T00:36:29.076Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-114052'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-823j-m4cj-hmjf
    label: GitHub Security Advisory (GHSA-823j-m4cj-hmjf)
  - url: >-
      https://www.vulncheck.com/advisories/vllm-0.25.0-before-0.31.0-moss-audio-memory-exhaustion-via-tokenize-mm-processor-kwargs
    label: >-
      VulnCheck Advisory: vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion
      via /tokenize mm_processor_kwargs
tags:
  - cve.org
ingestedAt: '2026-10-21T01:37:08.043Z'
---

## Overview

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized mel_config values to the /tokenize endpoint, which bypasses --api-key, to exhaust host memory and crash the API process.

## Affected

- `vllm >= 0.25.0 < 0.31.0`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.