CVE-2026-105760
Medium
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.
SeverityMedium
CVSS5.3
Exploit probability—
ProductVllm
PublishedOct 5, 2026
First seenOct 5, 2026
Weakness typeCWE-400Uncontrolled resource consumption
How to fix
Update
- vllm vllm0.30.0 or later
- vllm0.30.0 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm vllm | 0.23.0 ≤ v < 0.30.0 | 0.30.0 |
| vllmPyPI | 0.23.0rc2 ≤ v < 0.30.0 | 0.30.0 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.