CVE-2026-73559 vLLM: Completion prompt lists fan out into unbounded engine requests
An authenticated user can cause resource exhaustion and denial of service by submitting a completion request with an unbounded list of prompts.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-73559?
CVE-2026-73559 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 13 Aug 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.
Weakness: CWE-400
Which versions are affected by CVE-2026-73559?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.19.0 | 0.26.0 |
vllm PyPI | From 0.19.0 | 0.26.0 |
vllm PyPI | From 0.19.0 | 0.26.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-73559?
Upgrade vllm to 0.26.0 or later.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-73559 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-73559 exists.
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-87x5-vmc3-756j, MINI-669x-hpx7-64m9, MINI-68hr-m52v-8fr2, MINI-vh25-68rj-6x85, PYSEC-2026-3704.