CVE-2026-93436
vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
CVSS 4.0 8.7 HIGHCVSS 3.1 7.5 HIGHCheck source for fixed versionsKEV status unknown
Historical advisory recorded 23 Oct 2026 15:48:27 UTC. Read the latest advisory.
cve-program · CVE-2026-93436
PublishedvLLM 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.
Read the publisher's advisoryAffected versions, risk and source history
Related advisories and sources
Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.
CVE-2026-93436 · CVE overview and exploitation status
cve-program · CVE-2026-93436
- https://github.com/vllm-project/vllm/pull/55677
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181
- https://github.com/vllm-project/vllm
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests
This historical advisory does not include today's related changes. Open the latest advisory to find current connections.