{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.12.0, \u003c 0.24.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "BBDCA379-5844-47A0-9217-A26C248DC441",
              "versionEndExcluding": "0.24.0",
              "versionStartIncluding": "0.12.0",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0."
    }
  ],
  "id": "CVE-2026-55514",
  "lastModified": "2026-07-07T19:02:37.753",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 6.5,
          "baseSeverity": "MEDIUM",
          "confidentialityImpact": "NONE",
          "integrityImpact": "NONE",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 3.6,
        "source": "nvd@nist.gov",
        "type": "Primary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 7.1,
          "baseSeverity": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "exploitMaturity": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "privilegesRequired": "LOW",
          "providerUrgency": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "userInteraction": "NONE",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/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",
          "version": "4.0",
          "vulnAvailabilityImpact": "HIGH",
          "vulnConfidentialityImpact": "NONE",
          "vulnIntegrityImpact": "NONE",
          "vulnerabilityResponseEffort": "NOT_DEFINED"
        },
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-55514",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-07-06T20:45:29.132412Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-07-06T21:16:57.207",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Issue Tracking",
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/pull/45252"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Release Notes"
      ],
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.24.0"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Vendor Advisory"
      ],
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-617"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Primary"
    }
  ]
}

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.12.0"
            },
            {
              "fixed": "0.24.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-55514"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-617"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-07-20T19:13:07Z",
    "nvd_published_at": "2026-07-06T21:16:57Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n_Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server._\n\nSending a pure prompt embeds payload in a `/v1/completions` request with a model using M-RoPE causes the EngineCore to fail an assertion and fatally crash, shutting down the entire server application.\n\nAny remote user who is authorized to make a `/v1/completions` endpoint can trivially make such a request and induce a crash.\n\n### Details\n_Give all details on the vulnerability. Pointing to the incriminated source code is very helpful for the maintainer._\n\nIn commit [56669c1](https://github.com/vllm-project/vllm/commit/56669c1f293d5c53b6a19ddf2f78802fa9fff2c2), a simple assert intended to be a type-narrowing assert was added to the `_init_mrope_positions` method in `GPUModelRunner` (the offending line on main at the time of writing: https://github.com/vllm-project/vllm/blob/2d481f8a946ee0521872af0f098674a8ee01ce4a/vllm/v1/worker/gpu_model_runner.py#L1588-L1607).\n\n```python\nassert req_state.prompt_token_ids is not None, (\n            \"M-RoPE requires prompt_token_ids to be available.\"\n        )\n```\n\nThis type narrowing assert is to prevent mypy errors later in the function because `None` is not a valid type for `mrope_model.get_mrope_input_positions`. Unfortunately, this assertion is not always true. `/v1/completions` requests that specify `prompt=None` and `prompt_embeds=\u003cnot none\u003e` will indeed create a CachedRequestState where `prompt_token_ids` is `None`. This triggers the assertion, which in turn crashes the EngineCore and the Server application.\n\n```\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py\", line 3997, in execute_model\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     deferred_state_corrections_fn = self._update_states(scheduler_output)\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py\", line 1239, in _update_states\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     self._init_mrope_positions(req_state)\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py\", line 1582, in _init_mrope_positions\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     assert req_state.prompt_token_ids is not None, (\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167] AssertionError: M-RoPE requires prompt_token_ids to be available.\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] AsyncLLM output_handler failed.\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] Traceback (most recent call last):\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py\", line 660, in output_handler\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]     outputs = await engine_core.get_output_async()\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py\", line 1030, in get_output_async\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]     raise self._format_exception(outputs) from None\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.\n```\n\nAll requests using the `/v1/chat/completions` endpoints will have text/`prompt_token_ids` parts (corresponding to the chat template), and `prompt_embeds` parts are handled as mm_features. This method (rightly) filters out those `prompt_embeds` content parts as they are treated as text positions.\n\nA sufficient solution to type narrowing here without raising a fatal assertion is to instead replace the assertion with a using dummy token ids:\n\n```python\ndef _init_mrope_positions(self, req_state: CachedRequestState):\n    model = self.get_model()\n    assert supports_mrope(model), \"M-RoPE support is not implemented.\"\n    mrope_model = cast(SupportsMRoPE, model)\n\n    # Filter out prompt_embeds modality (text-only position info)\n    mrope_features = [\n        f for f in req_state.mm_features if f.modality != \"prompt_embeds\"\n    ]\n    \n    # Handle both token_ids and embeddings-only inputs\n    if req_state.prompt_token_ids is not None:\n        input_tokens = req_state.prompt_token_ids\n    elif req_state.prompt_embeds is not None:\n        # For text-only embeddings, dummy token IDs are safe since\n        # get_mrope_input_positions only uses len(input_tokens) when mm_features is empty\n        seq_len = req_state.prompt_embeds.shape[0]\n        input_tokens = list(range(seq_len))\n        # Verify no mm_features remain (should be true after prompt_embeds filter)\n        assert len(mrope_features) == 0, (\n            \"M-RoPE with prompt_embeds-only input should have no multimodal features\"\n        )\n    else:\n        raise ValueError(\n            \"M-RoPE requires either prompt_token_ids or prompt_embeds.\"\n        )\n\n    req_state.mrope_positions, req_state.mrope_position_delta = (\n        mrope_model.get_mrope_input_positions(\n            input_tokens,\n            mrope_features,\n        )\n    )\n```\n\nTechnically, in isolation, this method still crashes in the case where `req_state.prompt_token_ids is None and req_state.mm_features`, so the solution above still leaves that potential vector open. As far as can be determined, however, such a `req_state` is impossible in the first place in online mode, because it would require a `/v1/completions` request with `prompt_embeds` AND multimodal features, but the `/v1/completions` request schema does not expose multimodal inputs in any discernible way. Today, those are the only two endpoints with `prompt_embeds` support. \n\nWhen in offline mode, it *is technically* possible to directly create an `EngineCoreRequest` that has `prompt_embeds and not prompt_token_ids and mm_features`, and pass that to `LLM.generate`. That would trigger this same assertion, and no validation would prevent that combination. It is strongly suspected, though, that this combination would be undefined in any model that support M-RoPE, because it would not be possible to determine which token positions correspond to `mm_features`. The proposed solution above would end up not setting `req_state.mrope_positions` and `req_state.mrope_position_delta` in this scenario, which could result in undefined behavior.\n\n`prompt_embeds` is far more familiar here than M-RoPE, and it is understood that each model that supports it is responsible for defining its own `get_mrope_input_positions` which have varying implementations. There is insufficient knowledge to be prescriptive in how the two features should interact in the offline case, other than possibly raising a validation error earlier on preventing that combination (which would emulate the current assertion behavior). Regardless, in offline mode, the chances of a remote user being able to exploit this are slim-to-nil compared to the online case which is incredibly straightforward.\n\n### Impact\n_What kind of vulnerability is it? Who is impacted?_\n\n- Denial of Service caused by an incorrect assertion inside of the `GPUModelRunner` which causes a fatal EngineCore exception\n- Any configuration with `--enable-prompt-embeds` and M-RoPE-supported model is vulnerable\n- The attack is extremely easy from the remote attacker\u0027s perspective (copying the official `prompt_embeds` online mode docs examples almost-verbatim, accounting for model-name and connection details, of course, will induce a guaranteed shutdown)",
  "id": "GHSA-33cg-gxv8-3p8g",
  "modified": "2026-07-20T19:13:07Z",
  "published": "2026-07-20T19:13:07Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-55514"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/45252"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2303.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.24.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "vLLM denial of service via prompt embeds on M-RoPE models"
}

{
  "affected": [
    {
      "ecosystem_specific": {},
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.12.0"
            },
            {
              "fixed": "0.24.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.12.0",
        "0.13.0",
        "0.14.0",
        "0.14.1",
        "0.15.0",
        "0.15.1",
        "0.16.0",
        "0.17.0",
        "0.17.1",
        "0.18.0",
        "0.18.1",
        "0.19.0",
        "0.19.1",
        "0.20.0",
        "0.20.1",
        "0.20.2",
        "0.21.0",
        "0.22.0",
        "0.22.1",
        "0.23.0"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-55514",
    "GHSA-33cg-gxv8-3p8g"
  ],
  "details": "vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.",
  "id": "PYSEC-2026-2303",
  "modified": "2026-07-13T05:52:25.622117Z",
  "published": "2026-07-06T21:16:57.207Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.24.0"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/45252"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ]
}