CVE-2026-116180
vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors
- State
- Published
- Severity
- 8.3 High
- Published
- Oct 25, 2026
- Updated
- Oct 26, 2026
- Reserved
- Oct 25, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 8.3 High | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H | VulnCheck |
| 3.1 | 7.7 High | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H | VulnCheck |
Weaknesses
- CWE-908 Use of Uninitialized Resource
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
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.