CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

What is CVE-2026-105760?

CVE-2026-105760 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 5 Oct 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.

Weakness: CWE-400

Which versions are affected by CVE-2026-105760?

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

Products include Vllm Vllm.

How do I fix CVE-2026-105760?

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-2026-105760 being exploited?

There is no known exploitation of CVE-2026-105760 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-58v5-2m8f-94pr, MINI-ggw3-9mm2-x4m9, MINI-m33q-hwgg-4x7m, PYSEC-2026-4307.