This paper presents a new technique to reduce memory usage and speed up inference for large neural networks, allowing them to run on consumer hardware with limited memory. A practitioner might care about this because it enables the deployment of large models in edge devices and reduces the need for expensive storage.
Firehose
Filtered to tagged “mixture-of-experts” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 89continual learning 27AI 23AI safety 13reinforcement learning 13agentic coding 12open-weight models 12AI agents 10machine learning 9AI ethics 8cybersecurity 8existential risk 8language models 8natural language processing 8ethics 7Reinforcement learning 6Diffusion models 5large language models 5multi-agent systems 5open-source 5recursive self-improvement 5robotics 5security 5software development 5Agentic AI 4artificial general intelligence 4mathematics 4Recursive self-improvement 4agents 3AI infrastructure 3
This paper addresses the issue of memory peak allocation in Mixture-of-Experts (MoE) models during long-context training, proposing four different techniques to reduce memory usage without compromising performance. Practitioners might care about these techniques to train larger MoE models with longer context lengths.