CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service
Attackers can crash the vLLM EngineCore by sending invalid cache_salt values in LMCache-MP deployments, denying service to all users.
- 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-2026-105756?
CVE-2026-105756 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 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.
Which versions are affected by CVE-2026-105756?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.30.0 |
vllm PyPI | All versions | 0.30.0 |
vllm PyPI | All versions | 0.30.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-105756?
Upgrade vllm to 0.30.0 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-2026-105756 being exploited?
There is no known exploitation of CVE-2026-105756 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-2823-qmq8-rwvj, MINI-fhqv-7983-7r7x, MINI-gr5h-c4rq-9g65, MINI-wqcw-fw9w-2m29, PYSEC-2026-4306.