ZDF
Sign inSign up

Vulnerabilities

Vulnerability · CVE-2026-44223

vLLM is an inference and serving engine for large language models (LLMs).

Published May 12, 2026 · catalog updated Jun 22, 2026 · vLLM is an inference

Check if you run it

No confirmed exploitation is on record for CVE-2026-44223. EPSS is 0.43%. Act only if a listed version of vLLM is an inference is installed.

Gaps on this record

  • The stored product name is a package slug. The name on this page is taken from the title (vLLM is an inference).
  • No version range is stored. A customer cannot check an installed version against this record.
  • No vendor fix or required action is stored. Compare the linked advisory before you change production.
Severity
Medium6.5
Known exploitation
Not in CISA/VulnCheck KEV
EPSS
0.43%
Remediation
Advisory link
Affected products
cpe vllm/vllm

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.

Are you affected?

Enter the version you run. The result uses only the ranges stored on this record.

The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.

  • cpe vllm/vllmversion unspecified

How to fix CVE-2026-44223

What to do

Three questions, each answered from this record only. Confirm the vendor advisory before you patch.

Should you patch?

No confirmed exploitation is on record for CVE-2026-44223. EPSS is 0.43%. Act only if a listed version of vLLM is an inference is installed.

Which versions are affected?

Affected version ranges are not on this record. Compare the installed version with the linked vendor advisory before you change production.

What should an analyst verify?

CWE-131; CWE-704. EPSS 0.43%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. May 12, 2026 · NIST NVD

    Detected

    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_pena

  2. Jun 22, 2026 · NIST NVD

    Updated

    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_pena

Sources

  • CVE.orgVulnerability recordCVE-2026-44223

    Official CVE identifier

    cve.org
  • FIRST EPSSExploitation probabilityCVE-2026-44223

    30-day exploitation probability 0.4%

    first.org
  • NIST NVDVulnerability recordCVE-2026-44223

    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 En

    nvd.nist.gov

References

Freshness

Last verified in this catalog Oct 18, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.