vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. This issue is fixed in version 0.32.0.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686 Patch
- https://github.com/vllm-project/vllm/pull/59417 Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx Patch, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 6
- Cpes+1 CPE criteria (now 1)NVD modified 2026-10-28 15:37
- StatusPublished → AnalyzedNVD modified 2026-10-28 15:37
- StatusAwaiting Analysis → PublishedNVD modified 2026-10-26 17:08
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-26 18:34
- StatusReceived → PublishedNVD modified 2026-10-26 17:08
- First seenCVSS 6.5NVD modified 2026-10-26 18:17
Affected (CPE criteria) 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References 4
- https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686 Patch
- https://github.com/vllm-project/vllm/pull/59417 Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx Patch, Vendor Advisory