Vulnerability-Lookup

GHSA-PJFG-W894-9457

Vulnerability from github – Published: 2026-09-22 00:30 – Updated: 2026-09-22 00:30

Details

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing.

Severity

7.5 (High)


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

8.7 (High)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-94627"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-401"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-09-21T22:17:01Z",
    "severity": "HIGH"
  },
  "details": "vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing.",
  "id": "GHSA-pjfg-w894-9457",
  "modified": "2026-09-22T00:30:55Z",
  "published": "2026-09-22T00:30:55Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-94627"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/49796"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/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",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-94627 (GCVE-0-2026-94627)

Vulnerability from cvelistv5 – Published: 2026-09-21 22:04 – Updated: 2026-09-21 22:04

Title

vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision

Summary

Severity

8.7 (High)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

7.5 (High)


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

CWE

CWE-401 - Missing Release of Memory after Effective Lifetime

Assigner

VulnCheck mitre root

References

4 references

URL	Tags
https://github.com/vllm-project/vllm/pull/49796	issue-trackingpatch
https://github.com/vllm-project/vllm/blob/v0.29.0…	technical-description
https://github.com/vllm-project/vllm	product
https://www.vulncheck.com/advisories/vllm-through…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version
vllm-project	vllm	Affected: 0 , ≤ 0.29.0 (semver) cpe:2.3:a:vllm:vllm::::::::

Date Public

2026-07-25 00:00

Credits

Mingkai Yu Jiapeng Li Jiajia Liu

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/vllm",
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "lessThanOrEqual": "0.29.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                  "versionEndIncluding": "0.29.0",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Mingkai Yu"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiapeng Li"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiajia Liu"
        }
      ],
      "datePublic": "2026-07-25T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.7,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.5,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-401",
              "description": "Missing Release of Memory after Effective Lifetime",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-21T22:04:16.559Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "Pull Request #49796",
          "tags": [
            "issue-tracking",
            "patch"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/49796"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/vllm-project/vllm"
        },
        {
          "name": "VulnCheck Advisory: vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision"
        }
      ],
      "title": "vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-94627",
    "datePublished": "2026-09-21T22:04:16.559Z",
    "dateReserved": "2026-09-21T21:42:30.080Z",
    "dateUpdated": "2026-09-21T22:04:16.559Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

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.

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

GHSA-PJFG-W894-9457

CVE-2026-94627 (GCVE-0-2026-94627)

Tags

Sightings

Nomenclature

Related by attack behaviour