Efficient Training on Multiple Consumer GPUs with RoundPipe Paper • 2604.27085 • Published Apr 29 • 46
DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation Paper • 2603.07416 • Published Mar 8 • 1
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference Paper • 2504.05897 • Published Apr 8, 2025 • 21
AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference Paper • 2408.10284 • Published Aug 19, 2024 • 1
