vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision
cve-program · CVE-2026-94627 · Published
No access to your tenant or devices. Every item links to its source. What this means
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.
Read the publisher's advisoryCISA KEV lists vulnerabilities known to be exploited. FIRST EPSS estimates the likelihood of exploitation in the next 30 days. An unavailable score does not mean zero risk.
This view includes predictions for CVE identifiers explicitly listed in public NuGet advisories. Microsoft release pages have their own prediction coverage. Check source status for the scope and latest checks.
No exploitation or prediction data is available here for these CVEs. This does not mean they are safe or unlikely to be exploited.
Compare earlier KEV listings and daily EPSS scores. Advisory wording and affected versions have a separate history.
A prediction change is reported when EPSS rises from below 10% to 10% or higher. Other daily score changes remain in this history.
See how the publisher's advisory changed over time. Each link opens the version saved at that time. The publisher's update date can differ from the date shown here.
Each link identifies one complete publisher record. History can include advisories that previously shared an identifier; an identifier removed by a publisher no longer establishes a current relationship. A historical link shows only that record and earlier saved versions. Failed checks and unchanged reads do not create new versions.
cve-program · CVE-2026-94627 · Published