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.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65 Patch
- https://github.com/vllm-project/vllm/pull/45252 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 7.1 · vllmNVD modified 2026-10-25 20:10
Affected (CPE criteria) 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References 4
- https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65 Patch
- https://github.com/vllm-project/vllm/pull/45252 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g Vendor Advisory