Adria Grondin, developer of the Locally AI app, provides a technical walkthrough on running large language models like Google's Gemma on an iPhone using Apple's MLX framework. The talk covers the necessary tools, performance expectations, the importance of quantization, and the growing MLX ecosystem.
Learn how AI model compression and quantization techniques are essential for optimizing Large Language Model (LLM) performance and significantly reducing inference costs in production. This deep dive covers practical examples, benefits like reduced latency and increased throughput, and strategies for different AI use cases, demonstrating how to deploy scalable AI with minimal accuracy degradation.
Guanhua Wang from Microsoft's DeepSpeed team explains ZeRO++, a system that tackles the communication bottleneck in large-scale LLM training. By quantizing weights and gradients, ZeRO++ reduces communication volume by 4x, leading to training speedups of over 2x, particularly in low-bandwidth and small-batch-size environments.