CVE-2025-62426CWE-770denial-of-service

CVE-2025-62426

Medium · published November 21, 2025

CVSS v3.1
6.5
EPSS
1%
Percentile
44.5
In the wild
Unconfirmed
What it is

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

The record
Technical detail
CVSS v3.1
6.5 · MEDIUM
Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS v4.0
Not supplied
EPSS
0.00538 · 44.5th percentile
Weakness
CWE-770 · Allocation of Resources Without Limits or Throttling
Published
2025-11-21T07:15Z
Affected products (3)
ProductVersionsFixed in
vllm/vllm≥ 0.5.5, < 0.11.10.11.1
vllm/vllmall versions—
vllm/vllmall versions—
References (5)
https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610 · [email protected]https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814 · [email protected]https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b · [email protected]https://github.com/vllm-project/vllm/pull/27205 · [email protected]https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p · [email protected]
EPSS history
Timeline
  • 21 NOV 01:21Z
    vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
    cvelistv5