CVE-2026-53923
Full vulnerability record from the local CVENow database.
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.
View original CVE JSON
{
"id": "CVE-2026-53923",
"sourceIdentifier": "[email protected]",
"published": "2026-06-22T23:16:30.737",
"lastModified": "2026-10-25T23:10:00.167",
"vulnStatus": "Analyzed",
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0."
},
{
"lang": "es",
"value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Desde 0.5.5 hasta 0.23.1rc0, la truncación de enteros de las dimensiones del tensor en los kernels de desquantificación GGUF de vLLM (csrc/quantization/gguf/gguf_kernel.cu) provoca un procesamiento parcial del tensor. El tensor de salida se asigna a tamaño completo mediante torch::empty (memoria no inicializada), pero el kernel CUDA de desquantificación procesa solo un número truncado de elementos. La porción no rellenada del tensor de salida retiene lo que estuviera previamente en la memoria de la GPU. En implementaciones de inferencia multiusuario, esta memoria residual de la GPU puede contener datos de tensor de solicitudes de inferencia de otros usuarios, lo que constituye una revelación de información. Esta vulnerabilidad se corrige en 0.23.1rc0."
}
],
"affected": [
{
"source": "[email protected]",
"affectedData": [
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"version": ">= 0.5.5, < 0.23.1rc0",
"status": "affected"
}
]
}
]
}
],
"metrics": {
"cvssMetricV40": [
{
"source": "[email protected]",
"type": "Secondary",
"cvssData": {
"version": "4.0",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/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",
"baseScore": 5.3,
"baseSeverity": "MEDIUM",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"privilegesRequired": "NONE",
"userInteraction": "PASSIVE",
"vulnConfidentialityImpact": "LOW",
"vulnIntegrityImpact": "LOW",
"vulnAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"subAvailabilityImpact": "NONE",
"exploitMaturity": "NOT_DEFINED",
"confidentialityRequirement": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"availabilityRequirement": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"valueDensity": "NOT_DEFINED",
"vulnerabilityResponseEffort": "NOT_DEFINED",
"providerUrgency": "NOT_DEFINED"
}
}
],
"cvssMetricV31": [
{
"source": "[email protected]",
"type": "Primary",
"cvssData": {
"version": "3.1",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"privilegesRequired": "NONE",
"userInteraction": "NONE",
"scope": "UNCHANGED",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"availabilityImpact": "NONE"
},
"exploitabilityScore": 3.9,
"impactScore": 3.6
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"timestamp": "2026-06-23T15:04:15.555317Z",
"id": "CVE-2026-53923",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"version": "2.0.3"
}
}
]
},
"weaknesses": [
{
"source": "[email protected]",
"type": "Secondary",
"description": [
{
"lang": "en",
"value": "CWE-200"
},
{
"lang": "en",
"value": "CWE-681"
}
]
}
],
"configurations": [
{
"nodes": [
{
"operator": "OR",
"negate": false,
"cpeMatch": [
{
"vulnerable": true,
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"versionStartIncluding": "0.5.5",
"versionEndExcluding": "0.23.1",
"matchCriteriaId": "EC2E4E13-D3B7-4A9F-AF31-A9CD7753B6F4"
}
]
}
]
}
],
"references": [
{
"url": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e",
"source": "[email protected]",
"tags": [
"Patch"
]
},
{
"url": "https://github.com/vllm-project/vllm/pull/44971",
"source": "[email protected]",
"tags": [
"Issue Tracking"
]
},
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4",
"source": "[email protected]",
"tags": [
"Third Party Advisory"
]
}
]
}