vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

MITRE NVD CVE.ORG JSON API Print: PDF PDF

Summary

CVECVE-2026-53923
StatePUBLISHED
AssignerGitHub_M
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-06-22 23:16:30 UTC
Updated2026-06-22 23:16:30 UTC
DescriptionvLLM 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.

Risk And Classification

Primary CVSS: v4.0 5.3 MEDIUM from [email protected]

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

Problem Types: CWE-200 | CWE-681 | CWE-681 CWE-681: Incorrect Conversion between Numeric Types | CWE-200 CWE-200: Exposure of Sensitive Information to an Unauthorized Actor

VersionSourceTypeScoreSeverityVector
4.0[email protected]Secondary5.3MEDIUMCVSS: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/C...
4.0CNADECLARED5.3MEDIUMCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N

CVSS v4.0 Breakdown

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
Passive
Confidentiality
Low
Integrity
Low
Availability
None
Sub Conf.
None
Sub Integrity
None
Sub Availability
None

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

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA Vllm-project Vllm affected >= 0.5.5, < 0.23.1rc0 Not specified

References

ReferenceSourceLinkTags
github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d... [email protected] github.com
github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4 [email protected] github.com
github.com/vllm-project/vllm/pull/44971 [email protected] github.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis
© CVE.report 2026 |

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report