vulnti.work

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmfo…

Medium CVSS 5.3
CVECVE-2026-73556
First seen2026-08-14 18:16 UTC
Disclosed2026-08-13 15:20 UTC
Last updated2026-08-14 18:16 UTC
Channel statusauto

Summary

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, 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 cata…

In-depth triage

No in-depth report has been generated yet (DR-003 v2 AI pipeline is under construction).

Sources

  • NVD DATABASE

Original Links

Timeline

  1. nvd_ingest NVD