Sparsing Law: Towards Large Language Models with Greater Activation Sparsity Paper • 2411.02335 • Published 24 days ago • 11
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity Paper • 2411.02335 • Published 24 days ago • 11
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity Paper • 2411.02335 • Published 24 days ago • 11 • 1
Configurable Foundation Models: Building LLMs from a Modular Perspective Paper • 2409.02877 • Published Sep 4 • 27
Configurable Foundation Models: Building LLMs from a Modular Perspective Paper • 2409.02877 • Published Sep 4 • 27
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models Paper • 2406.15718 • Published Jun 22 • 14
Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters Paper • 2406.05955 • Published Jun 10 • 22
PowerInfer-2: Fast Large Language Model Inference on a Smartphone Paper • 2406.06282 • Published Jun 10 • 36