CVE-2026-115914
Published:October 26, 2026
Updated:October 29, 2026
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.
Affected Packages
https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.11.1rc2 <v0.32.0Fix Suggestion:
Update to version v0.32.0vllm (PYTHON):
Affected version(s) >=0.11.1 <0.32.0Fix Suggestion:
Update to version 0.32.0Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
7.1
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
NONE
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
6.5
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH
Weakness Type (CWE)
Reachable Assertion
EPSS
Base Score:
0.39