Date: October 24, 2024
Time: 2:00PM ET / 11:00AM PT
Speaker: Robert Shaw, Sr. Director of Engineering at Neural Magic

Open-source large language models (LLMs) are now as robust as closed models, offering enterprises not only cutting-edge performance but also full control over deployment scenarios and privacy. With open-source AI solutions, you can tailor LLMs to your specific needs without vendor lock-in or prohibitive costs.

In this webinar, we’ll explain why optimized inference is key to maximizing the performance and efficiency of LLM deployments. By leveraging techniques like quantization and sparsity, you can significantly accelerate model responses and reduce infrastructure costs while maintaining model accuracy. 

With the combined power of vLLM, the most popular open-source inference server, and Neural Magic’s expertise, you can ensure scalable, high-performance LLM deployments that meet your enterprise needs. This session is perfect for ML engineers, data scientists, and decision-makers looking to scale AI efforts with cost-effective and high-performance AI solutions.

Join us to discover how to maximize the potential of open-source LLMs in your infrastructure. You’ll learn:

• How Neural Magic’s expertise in vLLM and LLM optimization will ensure your success at every step of the way
• Why open-source LLMs are as robust as proprietary alternatives
• How vLLM ensures best-in-class inference performance and seamless deployment on any hardware