Vulnerability · Published Oct 21, 2026 · Assigned by VulnCheck

CVE-2026-114052vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs

High 7.5

In plain English

A high-severity resource allocation without limits in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 43% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.5High

Exploit odds (30 days)0.5%top 56.6% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.31.0	PYSEC-2026-4361

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	0.25.0 – before 0.31.0

Weakness: CWE-770 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

GitHub Security Advisory (GHSA-823j-m4cj-hmjf) vendor-advisory
VulnCheck Advisory: vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs third-party-advisory