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

What is CVE-2026-116180?

CVE-2026-116180 is a high-severity vulnerability in Vllm Vllm, published on 25 Oct 2026.

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.

Weakness: CWE-908

Which versions are affected by CVE-2026-116180?

It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-116180?

No fix has been published for CVE-2026-116180 yet. Limit exposure of the affected software until one is available.

Is CVE-2026-116180 being exploited?

There is no known exploitation of CVE-2026-116180 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• GitHub advisory
• How this page is made

Also known as GHSA-rhcx-5729-88vg, GHSA-v8gv-gxpf-cg62.