{"cve":"CVE-2026-94627","nvd":{"published":"2026-09-21T22:17:01.740","modified":"2026-09-29T12:46:29.773","status":"Analyzed","description":"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.","cvss_v4":{"vector":"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","score":8.7},"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","score":7.5},"cwes":["CWE-401"],"references":["https://github.com/vllm-project/vllm","https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989","https://github.com/vllm-project/vllm/pull/49796","https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:55:23.253742848+00:00"},"epss":{"cve":"CVE-2026-94627","score":0.00627,"percentile":0.50066,"date":"2026-10-31"},"kev":null,"osv":[],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}