{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
            "extracted_events": [
              {
                "introduced": "0"
              },
              {
                "fixed": "0.24.0"
              }
            ],
            "source": [
              "CPE_RANGE",
              "REFERENCES"
            ]
          },
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "217c64a976869883fcf0c52a8cf8bc3c954d285b"
            },
            {
              "fixed": "8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-8wr5-jm2h-8r4f"
  ],
  "database_specific": {
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
      "CWE-1284",
      "CWE-20"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54234.json"
  },
  "details": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.",
  "id": "CVE-2026-54234",
  "modified": "2026-07-09T03:52:21.258669492Z",
  "published": "2026-07-06T19:49:20.481Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54234.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-54234"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/44744"
    }
  ],
  "schema_version": "1.7.5",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection"
}