UpHeron
All vulnerabilities

Servers and applications

CVE-2026-115911

DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

Severity
Medium 6.5
Published
20 Oct 2026
Last changed
30 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.32.0
Also known as
GHSA-542m-9234-8gvf
Sources
NVD, CVE Program, Project advisories (GitHub)

Description

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound.…

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • From 0.19.0 before 0.32.0
vLLMServers and applications · cpe:a:vllm:vllm
  • From 0.19.0 before 0.32.0
vLLMServers and applications · github:vllm-project/vllm
  • From 0.19.0 before 0.32.0

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-115911
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-115911
  • GitHub Advisory Database https://github.com/advisories/GHSA-542m-9234-8gvf
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf