VYPR
Medium severity6.5NVD Advisory· Published Nov 21, 2025· Updated Jun 17, 2026

CVE-2025-62426

CVE-2025-62426

Description

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
vllmPyPI
>= 0.5.5, < 0.11.10.11.1

Affected products

6
  • Vllm/Vllm4 versions
    cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*+ 3 more
    • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*range: >=0.5.5,<0.11.1
    • cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*
    • cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*
    • (no CPE)range: >= 0.5.5, < 0.11.1
  • osv-coords2 versions
    < 25.9.0_git20251112-r1+ 1 more
    • (no CPE)range: < 25.9.0_git20251112-r1
    • (no CPE)range: >= 0.5.5, < 0.11.1

Patches

Vulnerability mechanics

References

9

News mentions

0

No linked articles in our index yet.