| Component | vLLM |
| Severity | high (CVSS 7.7) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H |
| Published (NVD) | 2026-10-25 |
| Affected versions | >= 0.8.5, < 0.31.0 from the CVE Program record written by the CNA that assigned the CVE |
| Fixed in | 0.31.0 |
| Weakness | CWE-908 |
| CISA KEV | not listed |
NVD description
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
What to do
- Upgrade vLLM to
0.31.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-116180
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg
- https://www.vulncheck.com/advisories/vllm-from-0.8.5-before-0.31.0-cross-tenant-dos-via-uninitialized-logprobstensors