Skip to content
Heist/ feed
Back to feed
Medium

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

Type: advisorySources: OSV

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.

Products
Not specified
Affected versions
Not specified
Fixed versions
Not specified
CVEs
CVE-2026-105760
Confirmed fixed CVEs
Not specified
Updated in this feed
3 Nov 2026, 01:33 UTC · Revision 1

Source evidence

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

core-osv · Original source

Published 5 Oct 2026, 23:01 UTC

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.

osv:CVE-2026-105760
Complete source record
{
  "id": "67a461aafca769d8801efa49202c931f046342266606a38d707e2a1c03bc7c20",
  "url": "https://osv.dev/vulnerability/CVE-2026-105760",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion",
    "summary": "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.",
    "evidence": "osv:CVE-2026-105760",
    "products": [],
    "severity": "medium",
    "structured": {
      "id": "CVE-2026-105760",
      "aliases": [
        "CVE-2026-105760",
        "GHSA-58v5-2m8f-94pr",
        "PYSEC-2026-4307"
      ],
      "metrics": [
        {
          "type": "CVSS_V3",
          "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L"
        }
      ],
      "affected": [
        {
          "ranges": [
            {
              "repo": "https://github.com/vllm-project/vllm",
              "type": "GIT",
              "events": [
                {
                  "introduced": "78743ab5bffd381e88f97e1c8ba20473b0ae6d75"
                },
                {
                  "fixed": "9ed533eb4adfe48aef7e569a08daeccd2a773fed"
                },
                {
                  "fixed": "8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7"
                }
              ],
              "database_specific": {
                "extracted_events": [
                  {
                    "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                    "range": [
                      {
                        "introduced": "0.23.0"
                      },
                      {
                        "fixed": "0.30.0"
                      }
                    ],
                    "source": "CPE_RANGE"
                  },
                  {
                    "range": [
                      {
                        "fixed": "8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7"
                      }
                    ],
                    "source": "REFERENCES_COMMIT"
                  },
                  {
                    "range": [
                      {
                        "fixed": "9ed533eb4adfe48aef7e569a08daeccd2a773fed"
                      }
                    ],
                    "source": "REFERENCES_TAG",
                    "original_tag": "v0.30.0"
                  }
                ]
              }
            }
          ],
          "database_specific": {
            "source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-105760.json"
          }
        }
      ],
      "modified": "2026-10-28T02:30:25.055204551Z",
      "provider": "osv",
      "references": [
        "https://github.com/vllm-project/vllm/releases/tag/v0.30.0",
        "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105760.json",
        "https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr",
        "https://nvd.nist.gov/vuln/detail/CVE-2026-105760",
        "https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7",
        "https://github.com/vllm-project/vllm/pull/54935"
      ],
      "provider_metadata": {
        "cwe_ids": [
          "CWE-400"
        ],
        "cna_assigner": "GitHub_M",
        "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105760.json"
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-105760",
        "evidence": "/id"
      }
    ],
    "security_relevant": true,
    "severity_evidence": "/severity/0/score"
  },
  "source_id": "core-osv",
  "document_id": 491673,
  "published_at": "2026-10-05T23:01:54.972+00:00"
}