Start your free trial today.
Protect your organization with cutting-edge cybersecurity solutions designed for resilience and efficiency. Secure your digital assets with confidence.
Your Shield Against Threats
Unleash the Power of Cybersecurity
Boost Your Security, Enhance Your Business
We solve Your Cyber Challenges
Quick Links
Resources
Deepaegis Portals
2025 Deepaegis. All Rights Reserved.
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.
Published
October 21, 2026
Last Modified
October 21, 2026