SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference Paper • 2502.18137 • Published 1 day ago • 40
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing Paper • 2412.14711 • Published Dec 19, 2024 • 16
SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration Paper • 2411.10958 • Published Nov 17, 2024 • 53
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration Paper • 2410.02367 • Published Oct 3, 2024 • 48