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.
References
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577 | Patch |
| https://github.com/vllm-project/vllm/pull/47595 | Issue Tracking Patch |
| 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 |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v | Vendor Advisory |
Configurations
History
28 Sep 2026, 18:42
| Type | Values Removed | Values Added |
|---|---|---|
| References | () https://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577 - Patch | |
| References | () https://github.com/vllm-project/vllm/pull/47595 - Issue Tracking, Patch | |
| References | () https://github.com/vllm-project/vllm/releases/tag/v0.26.0 - Release Notes | |
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v - Vendor Advisory | |
| CPE | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | |
| First Time |
Vllm vllm
Vllm |
Information
Published : 2026-08-13 15:20
Updated : 2026-09-28 18:42
NVD link : CVE-2026-73556
Mitre link : CVE-2026-73556
CVE.ORG link : CVE-2026-73556
JSON object : View
Products Affected
vllm
- vllm