CVE-2026-44223

See a problem?
Please try reporting it to the source first.
Source
https://cve.org/CVERecord?id=CVE-2026-44223
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-44223.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-44223
Aliases
Downstream
Published
2026-05-12T19:58:40.862Z
Modified
2026-07-08T08:02:15.809494620Z
Severity
  • 6.5 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CVSS Calculator
Summary
vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
Details

vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extracthiddenstates 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 (repetitionpenalty, frequencypenalty, or presencepenalty). A single request with a penalty parameter (e.g., "repetitionpenalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

Database specific 
{
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/44xxx/CVE-2026-44223.json",
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
        "CWE-131",
        "CWE-704"
    ]
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Introduced
bcf2be96120005e9aea171927f85055a6a5c0cf6
Fixed
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1
Database specific 
{
    "source": [
        "AFFECTED_FIELD",
        "CPE_RANGE"
    ],
    "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
    "extracted_events": [
        {
            "introduced": "0.18.0"
        },
        {
            "fixed": "0.20.0"
        }
    ]
}

Database specific

source 
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-44223.json"