CVE-2026-115914
mediumvLLM is an inference and serving engine for large language models.
Vendor / product: Vllm — vllm
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.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Affected products
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
References
- https://github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686 security-advisories@github.com
- https://github.com/vllm-project/vllm/pull/59417 security-advisories@github.com
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 security-advisories@github.com
- https://github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx security-advisories@github.com