PT-2025-47650 · Vllm · Vllm

CVE-2025-62426

·

Published

2025-11-20

·

Updated

2026-07-07

CVSS v2.0

6.8

Medium

VectorAV:N/AC:L/Au:S/C:N/I:N/A:C
Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.5 through 0.11.0
Description vLLM is an inference and serving engine for large language models (LLMs). The /v1/chat/completions and /tokenize API endpoints accept a chat template kwargs request parameter that is not properly validated against the chat template. This allows a malicious actor to potentially block processing of the API server for an extended period, impacting all other requests. The chat template kwargs parameter is used in the code before validation.
Recommendations Update vLLM to version 0.11.1 or later.

Exploit

Fix

DoS

Allocation of Resources Without Limits

Found an issue in the description? Have something to add? Feel free to write us 👾

Weakness Enumeration

Related Identifiers

BDU:2025-14680
CVE-2025-62426
GHSA-69J4-GRXJ-J64P
PYSEC-2026-2012

Affected Products

Vllm