vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structuredoutputs.regex parameter in vllm/v1/structuredoutput/backendlmformatenforcer.py is passed to lmformatenforcer.RegexParser without compileregexwithtimeout or validation in validatestructuredoutputrequestlmformatenforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.
{
"cwe_ids": [
"CWE-1333",
"CWE-400"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73556.json",
"cna_assigner": "GitHub_M"
}