Vulnerability · Published Oct 5, 2026 · Assigned by GitHub_M

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

Medium 5.3

In plain English

A medium-severity uncontrolled resource consumption in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 22% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)5.3Medium

Exploit odds (30 days)0.3%top 77.5% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.30.0	GHSA-58v5-2m8f-94pr
PyPI	vllm	0.30.0	PYSEC-2026-4307

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	>= 0.23.0rc2, < 0.30.0

Weakness: CWE-400 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/54935 x_refsource_MISC
https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7 x_refsource_MISC
https://github.com/vllm-project/vllm/releases/tag/v0.30.0 x_refsource_MISC