CVEFinder.io

CVE-2026-44223

🔶 medium
🔍 Scan for this CVE
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

Description

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.

CVSS Score
6.5
Medium
EPSS Score
0.0
Exploit Probability
Published Date
2026-05-12
First Seen: 2026-05-17
📊 Relative Risk Intelligence

This CVE is Lower Risk - more severe than 47.8% of all 326,604 vulnerabilities in our database.

#170,379
Below average severity
Severity Percentile
🎯 CISA SSVC Assessment Updated: May 15, 2026
🔍 Exploitation Status
Poc
Proof-of-concept available
⚙️ Automatable
NO
Requires human interaction
💥 Technical Impact
Partial
Limited system impact
SSVC data provided by CISA
Last Modified 2026-05-15
Source NVD 🔗
CVSS Vector 3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CWE IDs (Weakness Types)
CWE-131 CWE-704

📦 Affected Products 1

Vendor Product Status Affected Versions
vllm vllm Affected
> 0.18.0 < 0.20.0

🔗 References 2

https://github.com/vllm-project/vllm/pull/38610
Issue Tracking Patch
https://github.com/vllm-project/vllm/security/adviso...
Mitigation Vendor Advisory

🔗 Related CVEs 6

CVE ID Severity CVSS EPSS Summary Published
CVE-2026-44222 🔶 medium 6.5 0.0 vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Toke... 2026-05-12
CVE-2026-7141 🔶 medium 5.6 0.1 A vulnerability was found in vllm up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v... 2026-04-27
CVE-2026-34753 🔶 medium 5.4 0.0 vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side re... 2026-04-06
CVE-2026-34755 🔶 medium 6.5 0.1 vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.... 2026-04-06
CVE-2026-34756 🔶 medium 6.5 0.0 vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Servi... 2026-04-06
CVE-2026-34760 🔶 medium 5.9 0.1 vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, L... 2026-04-02
These CVEs affect the same products