CVE-2026-93436 — vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requ…
Published: 2026-09-17 · CVSS: 8.7 · CVSS 4.0
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7