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 chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chattemplatekwargs 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.
{
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62426.json",
"cwe_ids": [
"CWE-770"
],
"cna_assigner": "GitHub_M"
}