Vulnerability · Published May 12, 2026 · Assigned by GitHub_M
CVE-2026-44223vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
Medium 6.5
In plain English
A medium-severity security flaw in vllm from vllm-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 31% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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 packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.20.0 | GHSA-83vm-p52w-f9pw |
| PyPI | vllm | 0.20.0 | PYSEC-2026-145 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.18.0, < 0.20.0 |
Weakness: CWE-131, CWE-704 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/38610 x_refsource_MISC