CVE-2026-55514
Medium
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.
SeverityMedium
CVSS6.5
Exploit probability—
ProductVllm
PublishedJul 6, 2026
First seenJul 6, 2026
Weakness typeCWE-617CWE-617
How to fix
Update
- vllm vllm0.24.0 or later
- vllm0.24.0 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm vllm | 0.12.0 ≤ v < 0.24.0 | 0.24.0 |
| vllmPyPI | 0.12.0 ≤ v < 0.24.0 | 0.24.0 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.