CVE-2026-93436
Severity CVSS v4.0:
HIGH
Type:
Unavailable / Other
Publication date:
17/09/2026
Last modified:
28/09/2026
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.
Impact
Base Score 4.0
8.70
Severity 4.0
HIGH
Base Score 3.x
7.50
Severity 3.x
HIGH
Vulnerable products and versions
| CPE | From | Up to |
|---|---|---|
| cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | 0.29.0 (including) |
To consult the complete list of CPE names with products and versions, see this page
References to Advisories, Solutions, and Tools
- https://github.com/vllm-project/vllm
- 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/pull/55677
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests


