CVE-2026-115916

{
  "id": "CVE-2026-115916",
  "sourceIdentifier": "[email protected]",
  "published": "2026-10-26T18:17:39.080",
  "lastModified": "2026-10-28T15:36:34.777",
  "vulnStatus": "Analyzed",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "version": "< 0.32.0",
              "status": "affected"
            }
          ]
        }
      ]
    }
  ],
  "metrics": {
    "cvssMetricV31": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "3.1",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
          "baseScore": 6.5,
          "baseSeverity": "MEDIUM",
          "attackVector": "NETWORK",
          "attackComplexity": "LOW",
          "privilegesRequired": "LOW",
          "userInteraction": "NONE",
          "scope": "UNCHANGED",
          "confidentialityImpact": "NONE",
          "integrityImpact": "NONE",
          "availabilityImpact": "HIGH"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 3.6
      }
    ]
  },
  "weaknesses": [
    {
      "source": "[email protected]",
      "type": "Primary",
      "description": [
        {
          "lang": "en",
          "value": "CWE-129"
        },
        {
          "lang": "en",
          "value": "CWE-193"
        }
      ]
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "operator": "OR",
          "negate": false,
          "cpeMatch": [
            {
              "vulnerable": true,
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "versionEndExcluding": "0.32.0",
              "matchCriteriaId": "F7BDDF1C-9078-4F18-A972-846C4C1363E5"
            }
          ]
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229",
      "source": "[email protected]",
      "tags": [
        "Patch"
      ]
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/59491",
      "source": "[email protected]",
      "tags": [
        "Patch"
      ]
    },
    {
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
      "source": "[email protected]",
      "tags": [
        "Release Notes"
      ]
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4",
      "source": "[email protected]",
      "tags": [
        "Patch",
        "Vendor Advisory"
      ]
    }
  ]
}