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.

CVSS v3 6.5 MEDIUM

6.5^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 3.9 / Impact : 2.5

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact NONE

Integrity Impact LOW

Availability Impact LOW

Scope UNCHANGED

References

Link	Resource
https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198	Patch
https://github.com/vllm-project/vllm/pull/45116	Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823	Exploit Third Party Advisory

Configurations

Configuration 1 (hide)

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

History

25 Oct 2026, 23:10

Type	Values Removed	Values Added
Summary		(es) vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLMs). Antes de 0.23.1rc0, las compuertas de validación de temperatura de ll usan operadores de comparación (<, >), que se evalúan silenciosamente como Falso para NaN y para Infinito positivo en la semántica de punto flotante IEEE 754 de Python. Ambos valores pasan cada protección y se propagan a los kernels de muestreo de GPU, donde producen un comportamiento indefinido o errores de CUDA que pueden bloquear el trabajador de inferencia. Esta vulnerabilidad está corregida en 0.23.1rc0.

Information

Published : 2026-06-22 23:16

Updated : 2026-10-25 23:10

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

{"id": "CVE-2026-54235", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-54235", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-06-23T12:25:28.448086Z"}}], "cvssMetricV31": [{"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.5, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L", "integrityImpact": "LOW", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "LOW", "privilegesRequired": "NONE", "confidentialityImpact": "NONE"}, "impactScore": 2.5, "exploitabilityScore": 3.9}], "cvssMetricV40": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 6.9, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "LOW", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "< 0.23.1rc0"}]}]}], "published": "2026-06-22T23:16:31.143", "references": [{"url": "https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198", "tags": ["Patch"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/pull/45116", "tags": ["Issue Tracking"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823", "tags": ["Exploit", "Third Party Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-1287"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLMs). Antes de 0.23.1rc0, las compuertas de validaci\u00f3n de temperatura de ll usan operadores de comparaci\u00f3n (<, >), que se eval\u00faan silenciosamente como Falso para NaN y para Infinito positivo en la sem\u00e1ntica de punto flotante IEEE 754 de Python. Ambos valores pasan cada protecci\u00f3n y se propagan a los kernels de muestreo de GPU, donde producen un comportamiento indefinido o errores de CUDA que pueden bloquear el trabajador de inferencia. Esta vulnerabilidad est\u00e1 corregida en 0.23.1rc0."}], "lastModified": "2026-10-25T23:10:00.167", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "BF7F1CE7-1A95-41E3-95A5-732906527D08", "versionEndExcluding": "0.23.1"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}