{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-94627", "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "state": "PUBLISHED", "assignerShortName": "VulnCheck", "dateReserved": "2026-09-21T21:42:30.080Z", "datePublished": "2026-09-21T22:04:16.559Z", "dateUpdated": "2026-09-21T22:04:16.559Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "shortName": "VulnCheck", "dateUpdated": "2026-09-21T22:04:16.559Z"}, "datePublic": "2026-07-25T00:00:00.000Z", "title": "vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision", "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."}], "problemTypes": [{"descriptions": [{"lang": "en", "description": "Missing Release of Memory after Effective Lifetime", "cweId": "CWE-401", "type": "CWE"}]}], "affected": [{"vendor": "vllm-project", "product": "vllm", "defaultStatus": "unaffected", "packageURL": "pkg:pypi/vllm", "versions": [{"version": "0", "lessThanOrEqual": "0.29.0", "status": "affected", "versionType": "semver"}]}], "cpeApplicability": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "versionEndIncluding": "0.29.0"}]}]}], "metrics": [{"format": "CVSS", "cvssV4_0": {"version": "4.0", "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", "attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "NONE", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "baseScore": 8.7, "baseSeverity": "HIGH"}}, {"format": "CVSS", "cvssV3_1": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH", "baseScore": 7.5, "baseSeverity": "HIGH"}}], "references": [{"url": "https://github.com/vllm-project/vllm/pull/49796", "tags": ["issue-tracking", "patch"], "name": "Pull Request #49796"}, {"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": ["technical-description"]}, {"url": "https://github.com/vllm-project/vllm", "tags": ["product"]}, {"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"}], "credits": [{"lang": "en", "value": "Mingkai Yu", "type": "finder"}, {"lang": "en", "value": "Jiapeng Li", "type": "finder"}, {"lang": "en", "value": "Jiajia Liu", "type": "finder"}], "x_generator": {"engine": "vulncheck-endgame"}}}}

{}

{"affected": [{"affectedData": [{"defaultStatus": "unaffected", "packageURL": "pkg:pypi/vllm", "product": "vllm", "vendor": "vllm-project", "versions": [{"lessThanOrEqual": "0.29.0", "status": "affected", "version": "0", "versionType": "semver"}]}], "source": "disclosure@vulncheck.com"}], "cveTags": [], "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."}], "id": "CVE-2026-94627", "lastModified": "2026-09-21T22:17:01.740", "metrics": {"cvssMetricV31": [{"cvssData": {"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"}, "exploitabilityScore": 3.9, "impactScore": 3.6, "source": "disclosure@vulncheck.com", "type": "Primary"}], "cvssMetricV40": [{"cvssData": {"Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "Safety": "NOT_DEFINED", "attackComplexity": "LOW", "attackRequirements": "NONE", "attackVector": "NETWORK", "availabilityRequirement": "NOT_DEFINED", "baseScore": 8.7, "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": "NONE", "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: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", "version": "4.0", "vulnAvailabilityImpact": "HIGH", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "source": "disclosure@vulncheck.com", "type": "Secondary"}]}, "published": "2026-09-21T22:17:01.740", "references": [{"source": "disclosure@vulncheck.com", "url": "https://github.com/vllm-project/vllm"}, {"source": "disclosure@vulncheck.com", "url": "https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989"}, {"source": "disclosure@vulncheck.com", "url": "https://github.com/vllm-project/vllm/pull/49796"}, {"source": "disclosure@vulncheck.com", "url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision"}], "sourceIdentifier": "disclosure@vulncheck.com", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-401"}], "source": "disclosure@vulncheck.com", "type": "Primary"}]}

{}

{}