{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-53923", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-06-11T15:46:12.316Z", "datePublished": "2026-06-22T21:55:42.001Z", "dateUpdated": "2026-06-22T21:55:42.001Z"}, "containers": {"cna": {"title": "vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow", "problemTypes": [{"descriptions": [{"cweId": "CWE-681", "lang": "en", "description": "CWE-681: Incorrect Conversion between Numeric Types", "type": "CWE"}]}, {"descriptions": [{"cweId": "CWE-200", "lang": "en", "description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor", "type": "CWE"}]}], "metrics": [{"cvssV4_0": {"attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "PASSIVE", "vulnConfidentialityImpact": "LOW", "vulnIntegrityImpact": "LOW", "vulnAvailabilityImpact": "NONE", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "baseScore": 5.3, "baseSeverity": "MEDIUM", "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", "version": "4.0"}}], "references": [{"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4"}, {"name": "https://github.com/vllm-project/vllm/pull/44971", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/pull/44971"}, {"name": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e", "tags": ["x_refsource_MISC"], "url": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": ">= 0.5.5, < 0.23.1rc0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-06-22T21:55:42.001Z"}, "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."}], "source": {"advisory": "GHSA-5jv2-g5wq-cmr4", "discovery": "UNKNOWN"}}}}

{}

{}

{}

{"created": "2026-06-22T23:30:05.607643+00:00", "updated": "2026-06-22T23:30:05.607652+00:00", "vendors": [], "weaknesses": ["CWE-200", "CWE-681"]}