CVE-2026-44223
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.
Does this matter?
Lower severity and a low EPSS score (0.37%). Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 3.1
- 6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.37% probability · 30th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-131, CWE-704
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
- https://github.com/vllm-project/vllm/pull/38610Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pwMitigation, Vendor Advisory
- https://github.com/vllm-project/vllm/pull/38610Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pwMitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.