CVE-2026-73556
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/struct
CVSS
5.3
Medium
EPSS
—
KEV
—
Exploit Today
—
0-100
Published: Aug 13, 2026 · Last modified: Aug 14, 2026 · CWE-400 · CWE-1333
Not enough EPSS history yet.
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 catastrophic regular expression. This issue is fixed in version 0.26.0.
- github.comhttps://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577
- github.comhttps://github.com/vllm-project/vllm/pull/47595
- github.comhttps://github.com/vllm-project/vllm/releases/tag/v0.26.0
- github.comhttps://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v
- github.comhttps://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v