Vulnerability-Lookup

PYSEC-2026-2303

Vulnerability from pysec - Published: 2026-07-06 21:16 - Updated: 2026-07-13 05:52

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.

Severity

6.5 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "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"
    }
  ]
}

CVE-2026-55514 (GCVE-0-2026-55514)

Vulnerability from cvelistv5 – Published: 2026-07-06 20:07 – Updated: 2026-07-06 20:46

Title

vLLM denial of service via prompt embeds on M-RoPE models

Summary

Severity

7.1 (High)


                        
                          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

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-07-06 20:45 UTC

CWE

CWE-617 - Reachable Assertion

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7613 records in the last 180 days details

References

4 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/45252	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/47022…	x_refsource_MISC
https://github.com/vllm-project/vllm/releases/tag…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: >= 0.12.0, < 0.24.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-55514",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-06T20:45:29.132412Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-07-06T20:46:52.405Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.12.0, \u003c 0.24.0"
            }
          ]
        }
      ],
      "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."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "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",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-617",
              "description": "CWE-617: Reachable Assertion",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-06T20:07:40.405Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/45252",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/45252"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"
        },
        {
          "name": "https://github.com/vllm-project/vllm/releases/tag/v0.24.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/releases/tag/v0.24.0"
        }
      ],
      "source": {
        "advisory": "GHSA-33cg-gxv8-3p8g",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM denial of service via prompt embeds on M-RoPE models"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-55514",
    "datePublished": "2026-07-06T20:07:40.405Z",
    "dateReserved": "2026-06-16T22:44:22.284Z",
    "dateUpdated": "2026-07-06T20:46:52.405Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

GHSA-33CG-GXV8-3P8G

Vulnerability from github – Published: 2026-07-20 19:13 – Updated: 2026-07-20 19:13

Summary

vLLM denial of service via prompt embeds on M-RoPE models

Details

Summary

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.

Sending 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.

Any remote user who is authorized to make a /v1/completions endpoint can trivially make such a request and induce a crash.

Details

Give all details on the vulnerability. Pointing to the incriminated source code is very helpful for the maintainer.

In commit 56669c1, 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).

assert req_state.prompt_token_ids is not None, (
            "M-RoPE requires prompt_token_ids to be available."
        )

This 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=<not none> 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.

(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
(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     deferred_state_corrections_fn = self._update_states(scheduler_output)
(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(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
(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     self._init_mrope_positions(req_state)
(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
(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     assert req_state.prompt_token_ids is not None, (
(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167] AssertionError: M-RoPE requires prompt_token_ids to be available.
(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] AsyncLLM output_handler failed.
(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] Traceback (most recent call last):
(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
(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]     outputs = await engine_core.get_output_async()
(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(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
(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]     raise self._format_exception(outputs) from None
(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.

All 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.

A sufficient solution to type narrowing here without raising a fatal assertion is to instead replace the assertion with a using dummy token ids:

def _init_mrope_positions(self, req_state: CachedRequestState):
    model = self.get_model()
    assert supports_mrope(model), "M-RoPE support is not implemented."
    mrope_model = cast(SupportsMRoPE, model)

    # Filter out prompt_embeds modality (text-only position info)
    mrope_features = [
        f for f in req_state.mm_features if f.modality != "prompt_embeds"
    ]

    # Handle both token_ids and embeddings-only inputs
    if req_state.prompt_token_ids is not None:
        input_tokens = req_state.prompt_token_ids
    elif req_state.prompt_embeds is not None:
        # For text-only embeddings, dummy token IDs are safe since
        # get_mrope_input_positions only uses len(input_tokens) when mm_features is empty
        seq_len = req_state.prompt_embeds.shape[0]
        input_tokens = list(range(seq_len))
        # Verify no mm_features remain (should be true after prompt_embeds filter)
        assert len(mrope_features) == 0, (
            "M-RoPE with prompt_embeds-only input should have no multimodal features"
        )
    else:
        raise ValueError(
            "M-RoPE requires either prompt_token_ids or prompt_embeds."
        )

    req_state.mrope_positions, req_state.mrope_position_delta = (
        mrope_model.get_mrope_input_positions(
            input_tokens,
            mrope_features,
        )
    )

Technically, 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.

When 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.

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.

Impact

What kind of vulnerability is it? Who is impacted?

Denial of Service caused by an incorrect assertion inside of the GPUModelRunner which causes a fatal EngineCore exception
Any configuration with --enable-prompt-embeds and M-RoPE-supported model is vulnerable
The attack is extremely easy from the remote attacker's 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)

Severity

7.1 (High)


                  
                    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

Show details on source website

JSON

To clipboard

{
  "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"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

PYSEC-2026-2303

CVE-2026-55514 (GCVE-0-2026-55514)

GHSA-33CG-GXV8-3P8G

Summary

Details

Impact

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour