Abstract: Forget specialized hardware. Get GPU-class performance on your commodity CPUs with compound sparsity and sparsity-aware inference execution.
This talk will demonstrate the power of compound sparsity for model compression and inference speedup for NLP and CV domains, with a special focus on the recently popular Large Language Models. The combination of structured + unstructured pruning (to 90%+ sparsity), quantization, and knowledge distillation can be used to create models that run an order of magnitude faster than their dense counterparts, without a noticeable drop in accuracy. This key enabler allows fast inference of modern neural networks on CPUs. The session participants will learn the theory behind compound sparsity, state-of-the-art techniques, and how to apply it in practice using the Neural Magic platform.
Bio: Damian is engineer, roboticist, software developer, and problem solver. Previous experience in autonomous driving (Argo AI), AI in industrial robotics (Arrival), and building machines that build machines (Tesla). Currently working in Neural Magic, focusing on the sparse future of AI computation. Works towards unlocking creative and economic potential with intelligent robotics while avoiding the uprising of sentient machines.