technical

Why on-premises LLM guardrails are a dead-end?
Read More

Why on-premises LLM guardrails are a dead-end?

LLM guardrails principle

09 Apr 2026 Marwane El Hani
White-box LLM Attacks, or the Threat Everyone Ignores
Read More

White-box LLM Attacks, or the Threat Everyone Ignores

From Pixels to Sentences

09 Apr 2026 Marwane El Hani
How to Quantize an AI Model for Deployment?
Read More

How to Quantize an AI Model for Deployment?

Why Quantization? Today, AI models are becoming increasingly large, creating a critical need to reduce their size for deployment, particularly...

11 Feb 2026 Victor Guyomard
Can TensorRT AI Models Be Reverse-Engineered?
Read More

Can TensorRT AI Models Be Reverse-Engineered?

TensorRT for accelerating your AI models

26 Sep 2025 Ulysse-neo Lartigaud