CVE-2026-116180
7.7 HIGHpublic exploit availablePublished 2026-10-25 · Updated 2026-10-26
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H
Weaknesses
CWE-908
Public exploit & PoC references
All references
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- MEDIUMCVE-2026-102187
- MEDIUMCVE-2026-102300
- MEDIUMCVE-2026-102303
- MEDIUMCVE-2026-102307
- LOWCVE-2026-102311
- MEDIUMCVE-2026-102313
- LOWCVE-2026-102315
- LOWCVE-2026-102319
Related by shared AI tags and CWE weakness class. Browse the full archive.