Resource exhaustion in Vllm-project Vllm
CVE-2025-30202
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a mult…
EPSS: 0.004 (63.8th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
Affected products
- Vllm-project Vllm — versions >= 0.5.2, < 0.8.5
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-9f8f-2vmf-885j (x_refsource_CONFIRM)
- https://github.com/vllm-project/vllm/pull/6183 (x_refsource_MISC)
- https://github.com/vllm-project/vllm/commit/a0304dc504c85f421d38ef47c64f83046a13641c (x_refsource_MISC)
Frequently asked questions
- What is CVE-2025-30202?
- CVE-2025-30202 is a high-severity vulnerability in Vllm-project Vllm, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 7.5/10. Published 2025-04-30.
- How severe is CVE-2025-30202?
- High severity. CVSS v3 base score is 7.5 out of 10.