CVSS 4.0
8.7 highCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:NCVE-2026-93436
High (8.7) in vllm vllm. EPSS 0.8% chance of exploitation in the next 30 days. Fixed in vllm 0.30.0.
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.
Severity
CVSS 3.1
7.5 highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H- EPSS
- 0.8% chance of exploitation in the next 30 days; higher than 55% of CVEs (scores of 2026-10-31)
- CWE
- CWE-401
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| PYSEC-2026-3996 | PyPI | vllm | <0.30.0 | 0.30.0 |
References
- 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