Large models on CPUs
Practical AI
00:00
Optimizing AI Models: Techniques and Trends
This chapter explores the challenges of applying optimization techniques like quantization and pruning to enhance model performance while preserving accuracy. It highlights various methods, including training aware and post-training optimization, and discusses tools such as SparseMount and the upcoming Sparsify platform. The conversation emphasizes the importance of collaboration in the AI community to improve accessibility and usability of advanced optimization practices for practitioners.
Transcript
Play full episode
