Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🛡️
Not in CISA KEV
HIGH severity

CVE-2026-116180 — Vllm-project

HIGH

CVE-2026-116180 is a high-severity (CVSS 7.7) CWE-908 vulnerability. No vendor fix is recorded yet; mitigation options are listed below.

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…

Published
Updated
Affected
—
Patched
—
Exploits
None indexed
Exploitation data as of Oct 25, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

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.

Detection & mitigation playbook

Vulnerability

  1. Detect

    Identify every host running the affected component and compare the installed build against the fixed version below — for source-built or distro-packaged software the version string, not a lockfile, is the source of truth (`dpkg -l`, `rpm -q`, or the binary's own `--version`).

  2. Remediation status

    No fixed release is recorded for CVE-2026-116180 yet. Track the upstream advisory, and apply the exposure-reduction steps below in the meantime.

  3. Mitigate without a patch

    Stop feeding it untrusted input: reject or quarantine files and payloads from unverified sources until you can upgrade, restrict accepted formats to the ones you actually need, and run the parsing or decoding step in a least-privileged sandbox or short-lived worker so a crash or corrupted read cannot reach the rest of the process.

Frequently Asked Questions

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.
O3 Security · Impact-Aware SCA

Is CVE-2026-116180 in your dependencies?

Find it across , including transitive dependencies.

Scan my dependencies How O3 SCA works