CVE-2026-105753 vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core
An attacker can cause a denial of service in vLLM by triggering a cache desync that leads to an assertion failure in the engine core.
- 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-2026-105753?
CVE-2026-105753 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 5 Oct 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. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if that request is rejected. A later request reusing the same media hash causes MultiModalProcessorSenderCache to send no payload and MultiModalReceiverCache to reach an assertion with the message "Expected a cached item," producing a shared-service availability failure. This issue is fixed in version 0.28.0.
Weakness: CWE-617
Which versions are affected by CVE-2026-105753?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.28.0 |
vllm PyPI | All versions | 0.28.0 |
vllm PyPI | All versions | 0.28.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-105753?
Upgrade vllm to 0.28.0 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-2026-105753 being exploited?
There is no known exploitation of CVE-2026-105753 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-ph3r-5jfg-f84f, MINI-9hp5-mqg2-2jvh, MINI-pjjw-fgxc-6223, MINI-q7m6-x689-54r2, PYSEC-2026-4197.