{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "extracted_events": [
              {
                "introduced": "0.5.5"
              },
              {
                "fixed": "0.23.1rc0"
              }
            ],
            "source": [
              "AFFECTED_FIELD",
              "REFERENCES"
            ]
          },
          "events": [
            {
              "introduced": "09c7792610ada9f88bbf87d32b472dd44bf23cc2"
            },
            {
              "fixed": "f219788f91952827132fa4fdf916427cd20d225e"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-5jv2-g5wq-cmr4"
  ],
  "database_specific": {
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
      "CWE-200",
      "CWE-681"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/53xxx/CVE-2026-53923.json"
  },
  "details": "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.",
  "id": "CVE-2026-53923",
  "modified": "2026-07-08T05:36:30.532000440Z",
  "published": "2026-06-22T21:55:42.001Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/53xxx/CVE-2026-53923.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-53923"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/44971"
    }
  ],
  "schema_version": "1.7.5",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow"
}