Advisoriesby IbisvLLMPYSEC-2026-4361
vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability...
Fix: upgrade to 0.31.0 or later
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 versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | >= 0.24.0, < 0.31.0 | 0.31.0 |
Changes since it was listed
Severity: Unrated to High
Details and references
- CVSS 3.1
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Severity from
- NVD
- Also known as
- CVE-2026-114052, GHSA-823j-m4cj-hmjf
More vLLM advisories
All vLLM
vLLM: denial of serviceCVE-2026-116178fixed in 0.30.0vLLM: resource exhaustionCVE-2026-116177fixed in 0.25.0vLLM: denial of serviceCVE-2026-116173fixed in 0.24.0vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)CVE-2026-114055fixed in 0.31.0vLLM: insufficient authenticity checkCVE-2026-114050fixed in 0.31.0vLLM: authenticated attacker could collide shared cache keysCVE-2026-114054fixed in 0.31.0