CVE-2026-44223
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Summary
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 Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| vllm-project | vllm | >= 0.18.0, < 0.20.0 | affected |
Weaknesses
- CWE-131: CWE-131: Incorrect Calculation of Buffer Size
- CWE-704: CWE-704: Incorrect Type Conversion or Cast
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: poc
- Automatable: no
- Technical Impact: partial
Additional References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw
- https://github.com/vllm-project/vllm/pull/38610
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw
- https://github.com/vllm-project/vllm/pull/38610
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.