Resource exhaustion in Vllm
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/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.
Vulnerability class: DoS (Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 5.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L.
EPSS exploit prediction
EPSS 0.005, 44.5th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.26.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577 (Patch)
- https://github.com/vllm-project/vllm/pull/47595 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0 (Release Notes)
- https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v (Vendor Advisory)