HIGHVulnerability
Verified
Global
NVD HIGH: CVE-2026-114051 — vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/ge...
·Source: NIST NVD
Updated:
Executive Summary
vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart.
Analysis
vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart. CVSS Score: 7.5. Published: 2026-10-21T01:17:27.803.