Tensor Product Attention Is All You Need
Paper
•
2501.06425
•
Published
•
88
basic-blocs
-
-
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 50 -
Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer
Paper • 2503.02495 • Published • 8 -
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Paper • 2504.18415 • Published • 41