CVE-2026-94625: vLLM Resource Exhaustion Vulnerability in MooncakeConnector
Summary
CVE-2026-94625: vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Affects vllm versions < 0.30.0. Fixed in 0.30.0. How to fix ↓
Check if this vulnerability affects your application
Upload a manifest or SBOM and we'll show whether you're affected, plus every other risky package in the same scan.
No signup required · Results in about 60 seconds
Background
vLLM is an open-source library designed for efficient large language model serving. It provides functionalities for managing and executing tasks related to model inference. However, versions up to 0.29.0 are susceptible to a resource exhaustion vulnerability that can significantly impact performance and availability.
Vulnerability Detail
The vulnerability arises in the MooncakeConnector component of vLLM, where rejected prefill requests lead to the creation of ownerless transfer placeholders. These placeholders are never reclaimed, allowing attackers to exploit this behavior by sending a series of rejected requests. This can exhaust the sender task pools, resulting in delays of valid requests by as much as 480 seconds, even while health checks continue to report success. The issue is particularly concerning as it can lead to denial of service for legitimate users.
How To Fix
Latest published version: 0.32.0 as of 22 Oct 2026
pip install --upgrade "vllm==0.32.0"Upgrading to it may include breaking changes; the version below is the minimum fixed release for this vulnerability.
If you need the minimum change
0.30.0
This is the first release that contains the fix.
pip install --upgrade "vllm==0.30.0"Tip — Not sure which version your app runs? Vulert can match this fix to it. Scan free →
Workaround
As a temporary workaround, users can implement rate limiting on the number of requests sent to the MooncakeConnector to mitigate the impact of rejected requests. This can help manage the load on the sender task pools until the package is updated.
Conclusion
In summary, the vLLM package has a critical resource exhaustion vulnerability that can be exploited by attackers to delay valid requests. Users are strongly advised to upgrade to version 0.30.0 or later to mitigate this issue. Temporary workarounds such as rate limiting can help manage the risk until an upgrade is feasible.
See every vulnerability recorded for vllm →
FAQ
The vulnerability can lead to resource exhaustion, causing delays for valid requests and potentially resulting in denial of service for legitimate users.
You can use the Vulert playground at Vulert Scanner to check if your application is affected by this vulnerability without needing to sign up.
Versions of vLLM up to and including 0.29.0 are affected by this vulnerability.
Yes, the vulnerability has been patched in version 0.30.0 of the vLLM package.
If an immediate upgrade is not possible, consider implementing rate limiting on requests to reduce the risk of resource exhaustion.
Related vulnerabilities
Recent vulnerabilities recorded for vllm.
