view article Article DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency RadixArk • about 12 hours ago • 10
Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization Paper • 2611.11995 • Published 10 days ago • 56
Parallax: Parameterized Local Linear Attention for Language Modeling Paper • 2605.29157 • Published May 27 • 6
Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs Paper • 2503.06342 • Published Mar 8, 2025 • 1
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs Paper • 2410.13276 • Published Oct 17, 2024 • 29
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge Paper • 2407.00088 • Published Jun 25, 2024 • 12