CVE-2026-93436
vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
- State
- Published
- Severity
- 8.7 High
- Published
- Sep 17, 2026
- Updated
- Sep 24, 2026
- Reserved
- Sep 17, 2026
Description
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 8.7 High | 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 | VulnCheck |
| 3.1 | 7.5 High | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | VulnCheck |
Weaknesses
- CWE-401 Missing Release of Memory after Effective Lifetime
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
- https://github.com/vllm-project/vllm/pull/55677issue-trackingpatch
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181technical-description
- https://github.com/vllm-project/vllmproduct
- VulnCheck Advisory: vLLM through 0.29.0 Memory Exhaustion via Rejected Requeststhird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.