CVE-2026-69147

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.

Traduire en français

Produits concernés

• vllm-project vllm
• Vllm vllm

Scores CVSS

Faiblesses (CWE)

• CWE-400
• CWE-770

Références

• https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda Patch
• https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d Patch
• https://github.com/vllm-project/vllm/pull/47259 Issue TrackingPatch
• https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j ExploitVendor Advisory
• https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j ExploitVendor Advisory

Ailleurs

• NVD
• CVE.org
• CIRCL Vulnerability-Lookup
• CERT-FR
• GitHub Advisories