Medium severity5.3NVD Advisory· Published Aug 13, 2026· Updated Aug 14, 2026
CVE-2026-73556
CVE-2026-73556
Description
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.26.0 | 0.26.0 |
Affected products
2Patches
Vulnerability mechanics
References
6- github.com/advisories/GHSA-48jh-3gj7-fg8vghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-73556ghsaADVISORY
- github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577nvdWEB
- github.com/vllm-project/vllm/pull/47595nvdWEB
- github.com/vllm-project/vllm/releases/tag/v0.26.0nvdWEB
- github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8vnvdWEB
News mentions
0No linked articles in our index yet.