Tensor Product Attention Is All You Need
Paper
•
2501.06425
•
Published
•
89
SYS
-
-
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Paper • 2501.11873 • Published • 67 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 165 -
MoBA: Mixture of Block Attention for Long-Context LLMs
Paper • 2502.13189 • Published • 17 -
BitNet b1.58 2B4T Technical Report
Paper • 2504.12285 • Published • 74 -
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Paper • 2504.18415 • Published • 47 -
Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures
Paper • 2505.09343 • Published • 68 -
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Paper • 2505.22618 • Published • 42