Streamline your AI model deployment with Neural Magic

In January 2025, Red Hat acquired Neural Magic—a pioneer in software and algorithms that accelerate gen AI inference workloads —to tackle the challenges of enterprise AI and further democratize access to its transformative power through open source innovation.

Join this expert-led webinar to discover how to streamline and accelerate your gen AI models using Neural Magic capabilities—now part of Red Hat AI. 

You’ll learn about:

• vLLM, the leading open source runtime for accelerating and optimizing large language model (LLM) inference
• Inference Server, the latest addition to the Red Hat AI portfolio that brings vLLM to the enterprise
• How vLLM delivers high-performance inference on CPUs, reducing reliance on costly GPUs
• LLM Compressor and how to compress the LLMs of your choice
• The pre-optimized and validated models in Red Hat AI’s repository on Hugging Face and the new Red Hat model validation program
• GuideLLM, an open source tool that evaluates and enhances your LLM deployments for real-world inference
• Whether you're focused on performance, scalability, or cost-efficiency, this session will help you get more from your AI infrastructure