vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
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.
CVE-2026-105760
Primary source · Revision 1
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-105760
vllm
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
Structured affected-version data
Original package identities and version rules from this source.
[
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": ">= 0.23.0rc2, < 0.30.0"
}
]
}
]- Related CVEs
- CVE-2026-105760
Source reference:
/cveMetadata/cveId
Publisher severity
medium
Source reference: /containers/cna/metrics
- Event
- #9327 · Revision 1
- Added to Heist Feed
- Publisher date