CVE-2025-46560 vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
Attackers can cause denial of service in vLLM by submitting crafted inputs that trigger quadratic time complexity in token processing.
- 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-2025-46560?
CVE-2025-46560 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 30 Apr 2025. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.
Weakness: CWE-1333
Which versions are affected by CVE-2025-46560?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.8.0 | 0.8.5 |
vllm PyPI | From 0.8.0 | 0.8.5 |
vllm PyPI | From 0.8.0 | 0.8.5 |
Products include Vllm Vllm.
How do I fix CVE-2025-46560?
Upgrade vllm to 0.8.5 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-2025-46560 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-46560 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-vc6m-hm49-g9qg, PYSEC-2026-2022.