CVE-2026-116180
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 4.0
- 8.3
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 - CVSS 3.1
- 7.7
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H - CWE
- CWE-908
- Published
- Modified
- Record from
- the NVD, synced