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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-770"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62426.json"
}{
"cpe": [
"cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*",
"cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*"
],
"extracted_events": [
{
"introduced": "0.5.5"
},
{
"fixed": "0.11.1"
},
{
"introduced": "0.11.1-rc0"
},
{
"last_affected": "0.11.1-rc0"
},
{
"introduced": "0.11.1-rc1"
},
{
"last_affected": "0.11.1-rc1"
}
],
"source": [
"CPE_RANGE",
"CPE_STRING",
"REFERENCES"
]
}