{"cve":"CVE-2026-69147","nvd":{"published":"2026-09-16T18:17:11.770","modified":"2026-10-07T14:16:57.827","status":"Analyzed","description":"vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","score":6.5},"cwes":["CWE-400","CWE-770"],"references":["https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda","https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d","https://github.com/vllm-project/vllm/pull/47259","https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j","https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:54:41.405518556+00:00"},"epss":{"cve":"CVE-2026-69147","score":0.00583,"percentile":0.47583,"date":"2026-10-25"},"kev":null,"osv":[{"id":"GHSA-8pw2-6jv3-mj5j","url":"https://osv.dev/vulnerability/GHSA-8pw2-6jv3-mj5j","summary":"vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation","modified":"2026-10-01T17:55:52.391144765Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.28.0"],"fixed":["0.28.0"]}]},{"id":"PYSEC-2026-4178","url":"https://osv.dev/vulnerability/PYSEC-2026-4178","summary":"vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation","modified":"2026-10-01T17:45:09.325879460Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.28.0"],"fixed":["0.28.0"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}