CVE-2026-94623 vLLM through 0.29.0 Denial of Service via NIXL Multi-Prompt Assertion Failure

What is CVE-2026-94623?

CVE-2026-94623 is a high-severity denial of service vulnerability in Vllm Vllm, published on 21 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.

Weakness: CWE-617

Which versions are affected by CVE-2026-94623?

1 open source package ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-94623?

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-2026-94623 being exploited?

There is no known exploitation of CVE-2026-94623 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 Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-g3cp-v4cp-9xfq, MINI-3c3v-x66w-66q5, MINI-44f5-48wf-r9j4, MINI-c895-72vg-mv3x, PYSEC-2026-4005.