CVE-2026-116173 vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_ids
- Exploited in the wild
- Not known
- Fix
- Available
What is CVE-2026-116173?
CVE-2026-116173 is a high-severity vulnerability in Vllm Vllm, published on 25 Oct 2026.
Official description
vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing logprob_token_ids limits in the Rust gRPC frontend. Attackers can send Generate or GenerateStream requests with output_logprobs enabled and more than 128 output_candidates.token_ids, triggering a fatal sampler exception that crashes the engine.
Weakness: CWE-20
Which versions are affected by CVE-2026-116173?
1 open source package ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.22.0 | 0.24.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-116173?
Upgrade vllm to 0.24.0 or later.
Is CVE-2026-116173 being exploited?
There is no known exploitation of CVE-2026-116173 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
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-6pgw-f3pv-4h8q, GHSA-7r5r-rrjg-pf3c, PYSEC-2026-4350.