CVEvulnerability
CVE-2026-44223
6.5 MEDIUM
Official page ↗
- Status
- Modified
- Published
- 2026-05-12
- Last modified
- 2026-06-22
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-131, CWE-704
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.
Affected configurations
• vllm vllm (>= 0.18.0 < 0.20.0)
Related
References
- https://github.com/vllm-project/vllm/pull/38610 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw Mitigation, Vendor Advisory
- https://github.com/vllm-project/vllm/pull/38610 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw Mitigation, Vendor Advisory