Staging Environment: Content and features may be unstable or change without notice.
Search for vulnerabilities
Vulnerability details: VCID-jzjy-kj6h-4bas
Vulnerability ID VCID-jzjy-kj6h-4bas
Aliases CVE-2026-44223
GHSA-83vm-p52w-f9pw
PYSEC-2026-145
Summary vLLM is an inference and serving engine for large language models (LLMs). From 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.
Status Published
Exploitability None
Weighted Severity None
Risk None
Affected and Fixed Packages Package Details
Weaknesses (0)
There are no known CWE.
No exploits are available.
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Found at https://github.com/vllm-project/vllm/pull/38610
Attack Vector (AV) Attack Complexity (AC) Privileges Required (PR) User Interaction (UI) Scope (S) Confidentiality Impact (C) Integrity Impact (I) Availability Impact (A)

network

adjacent_network

local

physical

low

high

none

low

high

none

required

unchanged

changed

high

low

none

high

low

none

high

low

none

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Found at https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw
Attack Vector (AV) Attack Complexity (AC) Privileges Required (PR) User Interaction (UI) Scope (S) Confidentiality Impact (C) Integrity Impact (I) Availability Impact (A)

network

adjacent_network

local

physical

low

high

none

low

high

none

required

unchanged

changed

high

low

none

high

low

none

high

low

none

No EPSS data available for this vulnerability.

Date Actor Action Source VulnerableCode Version
2026-06-02T04:25:14.468033+00:00 Pypa Importer Import https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-145.yaml 38.6.0