Vulnerabilities

vLLM is an inference and serving engine for large language models.

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.

Read at NIST National Vulnerability Database (CVE API 2.0)

Product

AI / LLM tooling

CVSS

5.3

Fix

available

Exposure class

AI infrastructure

• NIST National Vulnerability Database (CVE API 2.0) (nvd.nist.gov)
• CVE-2026-105760 on this site · NVD · CVE.org · Vulnpedia

Other items that share a CVE or were clustered with this one.

1. 13
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 5.9 Fix available CVE-2026-105759 Prometheus
2. 8
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 5.3 CVE-2026-105758
3. 13
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 6.5 Fix available CVE-2026-105757
4. 13
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 6.5 Fix available CVE-2026-105756
5. 13
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 4.2 Fix available CVE-2026-105755
6. 8
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 6.5 CVE-2026-105754
7. 13
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 6.5 Fix available CVE-2026-105753
8. 5
   CVE NVD 28d ago

   vLLM is an inference and serving engine for large language models.

   CVSS 3.1 CVE-2026-105752