Vulnerability Description
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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.12.0, < 0.24.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff755Patch
- https://github.com/vllm-project/vllm/pull/45252Issue TrackingPatch
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8gVendor Advisory
FAQ
What is CVE-2026-55514?
CVE-2026-55514 is a vulnerability with a CVSS score of 6.5 (MEDIUM). 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 ...
How severe is CVE-2026-55514?
CVE-2026-55514 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-55514?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.