Vulnerability in Vllm
CVE-2026-55514
vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.
EPSS: 0.004 (30.3th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
Affected products
- Vllm
- Vllm-project Vllm — versions >= 0.12.0, < 0.24.0
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM, Vendor Advisory)
- security-advisories@github.com (Patch, x_refsource_MISC, Issue Tracking)
- security-advisories@github.com (Patch, x_refsource_MISC)
- security-advisories@github.com (x_refsource_MISC, Release Notes)
Frequently asked questions
- What is CVE-2026-55514?
- CVE-2026-55514 is a medium-severity vulnerability in Vllm, classified under Reachable Assertion. CVSS score: 6.5/10. Published 2026-07-06.
- How severe is CVE-2026-55514?
- Medium severity. CVSS v3 base score is 6.5 out of 10.