Vulnerability · Published Oct 25, 2026 · Assigned by VulnCheck

CVE-2026-116180vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors

High 7.7

In plain English

A high-severity security flaw in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 17% of all known vulnerabilities).

Severity (CVSS 3.1)7.7High

Exploit odds (30 days)0.3%top 82.9% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	0.8.5 – before 0.31.0

Weakness: CWE-908 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H

References

GitHub Security Advisory (GHSA-rhcx-5729-88vg) vendor-advisory
VulnCheck Advisory: vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors third-party-advisory