LF Insider: Optimize LLMs for Efficiency & Sustainability
This microcourse discusses strategies to reduce the energy consumption and computational demands of large language models (LLMs). To address this, the microcourse suggests optimizing LLMs through methods such as 4-bit quantization and utilizing energy-efficient hardware like Arm-based CPUs, specifically AWS Graviton instances. These approaches aim to enhance performance while minimizing environmental impact and operational costs.
Check out additional free content under LF Insider or Resources. For access to exclusive microlearning content (updated weekly), in addition to unlimited access to all of our e-learning courses and SkillCreds, take a look at our THRIVE-ONE Annual subscription.
