CVE-2026-116180
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.25%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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 4.0
- 8.3 HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.25% probability · 16th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-908
- Source
- disclosure@vulncheck.com
EPSS 0.2% since 26 October 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.