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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | >= 0.12.0, < 0.24.0 | — |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | vllm | >= 0.12.0, < 0.24.0 | 0.24.0 | GHSA-33cg-gxv8-3p8g |
Advisories 1
- WID-SEC-2026-2176 vllm: Mehrere Schwachstellen ermöglichen Denial of Service BSI CERT-Bund (WID) · Oct 26, 2026