{"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": "2026-09-22T12:51:23.062Z"}, "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"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-09-22T12:50:58.697049Z", "id": "CVE-2026-94627", "options": [{"Exploitation": "none"}, {"Automatable": "yes"}, {"Technical Impact": "partial"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-09-22T12:51:23.062Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"cna": {"title": "vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision", "credits": [{"lang": "en", "type": "finder", "value": "Mingkai Yu"}, {"lang": "en", "type": "finder", "value": "Jiapeng Li"}, {"lang": "en", "type": "finder", "value": "Jiajia Liu"}], "metrics": [{"format": "CVSS", "cvssV4_0": {"version": "4.0", "baseScore": 8.7, "attackVector": "NETWORK", "baseSeverity": "HIGH", "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", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE"}}, {"format": "CVSS", "cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.5, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "NONE"}}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "0", "versionType": "semver", "lessThanOrEqual": "0.29.0"}], "packageURL": "pkg:pypi/vllm", "defaultStatus": "unaffected"}], "datePublic": "2026-07-25T00:00:00.000Z", "references": [{"url": "https://github.com/vllm-project/vllm/pull/49796", "name": "Pull Request #49796", "tags": ["issue-tracking", "patch"]}, {"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"]}, {"url": "https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision", "name": "VulnCheck Advisory: vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision", "tags": ["third-party-advisory"]}], "x_generator": {"engine": "vulncheck-endgame"}, "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", "type": "CWE", "cweId": "CWE-401", "description": "Missing Release of Memory after Effective Lifetime"}]}], "cpeApplicability": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "vulnerable": true, "versionEndIncluding": "0.29.0"}], "operator": "OR"}]}], "providerMetadata": {"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "shortName": "VulnCheck", "dateUpdated": "2026-09-21T22:04:16.559Z"}}, "adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-94627", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "yes"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-09-22T12:50:58.697049Z"}}}], "providerMetadata": {"shortName": "CISA-ADP", "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "dateUpdated": "2026-09-22T12:51:18.153Z"}}]}, "cveMetadata": {"cveId": "CVE-2026-94627", "state": "PUBLISHED", "dateUpdated": "2026-09-21T22:04:16.559Z", "dateReserved": "2026-09-21T21:42:30.080Z", "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "datePublished": "2026-09-21T22:04:16.559Z", "assignerShortName": "VulnCheck"}, "dataVersion": "5.2"}

{"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": "2026-09-22T20:25:55.870", "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": "Secondary"}], "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"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-94627", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-09-22T12:50:58.697049Z", "version": "2.0.3"}}]}, "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": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-401"}], "source": "disclosure@vulncheck.com", "type": "Secondary"}]}

{"bugzilla": {"description": "vllm: vLLM: Denial of Service via GPU memory exhaustion", "id": "2537919", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2537919"}, "csaw": false, "cvss3": {"cvss3_base_score": "7.5", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "status": "draft"}, "cwe": "CWE-772", "details": ["A flaw was found in vLLM. A remote attacker can exploit a vulnerability in the Mooncake connector's management of GPU Key-Value (KV) cache block ownership. By submitting completion requests with multiple prompts that share a single transfer ID, attackers can cause orphaned KV cache blocks to accumulate. This leads to GPU memory exhaustion, ultimately preventing legitimate requests from being processed and resulting in a Denial of Service (DoS)."], "name": "CVE-2026-94627", "package_state": [{"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaiis/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-cpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-cuda-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-gaudi-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-neuron-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-rocm-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-spyre-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:ai_inference_server:3", "fix_state": "Affected", "package_name": "rhaii/vllm-tpu-rhel9", "product_name": "Red Hat AI Inference Server"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-aws-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-azure-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-azure-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-gaudi-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-gcp-cuda-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:3", "fix_state": "Affected", "package_name": "rhelai3/bootc-rocm-rhel9", "product_name": "Red Hat Enterprise Linux AI (RHEL AI) 3"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-kserve-agent-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-kserve-controller-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-kserve-router-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-kserve-storage-initializer-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-llm-d-kv-cache-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-th-torch-cuda-py312-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}, {"cpe": "cpe:/a:redhat:openshift_ai", "fix_state": "Affected", "package_name": "rhoai/odh-vllm-gaudi-rhel9", "product_name": "Red Hat OpenShift AI (RHOAI)"}], "public_date": "2026-09-21T22:04:16Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-94627\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-94627\nhttps://github.com/vllm-project/vllm\nhttps://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989\nhttps://github.com/vllm-project/vllm/pull/49796\nhttps://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision"], "threat_severity": "Important"}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,0.29.0]"}}], "enrichment": {"confidence": 95.0, "confidence_source": "inferred", "scores": [{"score": 95.0, "source": "inferred"}, {"score": 100.0, "source": "matching"}]}, "original": {"product": "vllm", "source": "cna", "vendor": "vllm-project"}, "product": "vllm", "vendor": "vllm"}], "created": "2026-09-21T23:30:18.231659+00:00", "updated": "2026-09-22T03:30:17.232465+00:00", "vendors": ["vllm", "vllm$PRODUCT$vllm"]}