← Back to CVE List
CVE-2026-93436NVD
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.
CVSS Base Metrics
CVSS v3 (3.1)
HIGH 7.5
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS v4 (4.0)
HIGH 8.7
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
Weaknesses (CWE)
CWE-401 - Missing Release of Memory after Effective Lifetime
Affected & Patched Versions
| Product | Affected Versions | Patched Version |
|---|---|---|
| vllm-project vllm | 0 - <= 0.29.0 | N/A |
References
- 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