CVE-2026-54235

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

24 Jun 2026, 16:53

Type Values Removed Values Added
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References () https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198 - () https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198 - Patch
References () https://github.com/vllm-project/vllm/pull/45116 - () https://github.com/vllm-project/vllm/pull/45116 - Issue Tracking
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823 - () https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823 - Exploit, Third Party Advisory
CVSS v2 : unknown
v3 : unknown
v2 : unknown
v3 : 6.5
First Time Vllm
Vllm vllm

22 Jun 2026, 23:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-06-22 23:16

Updated : 2026-06-24 16:53


NVD link : CVE-2026-54235

Mitre link : CVE-2026-54235

CVE.ORG link : CVE-2026-54235


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-1287

Improper Validation of Specified Type of Input