CVE-2026-105758 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach
Unauthenticated attackers can cause denial of service in vLLM by submitting excessive video frame parameters to the tokenize endpoint.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-105758?
CVE-2026-105758 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. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side ceilings. An unauthenticated caller can submit these values to the /tokenize endpoint, causing the sampler to decode every frame selected from attacker-controlled video input, consume disproportionate frontend memory, and potentially terminate the API process before scheduling or admission control. The Rust frontend is not affected because it rejects the media_io_kwargs field. This issue is fixed in version 0.30.0.
Weakness: CWE-770
Which versions are affected by CVE-2026-105758?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.24.0 | 0.30.0 |
vllm PyPI | From 0.24.0 | 0.30.0 |
vllm PyPI | From 0.24.0 | 0.30.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-105758?
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-2026-105758 being exploited?
There is no known exploitation of CVE-2026-105758 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-x6mc-67gf-chw4, MINI-23w5-pm9v-wh2f, MINI-fwvx-xj79-85gx, PYSEC-2026-4310.