Blog Tags GitHub

MoE

2 posts tagged with "MoE"

August 12, 2026

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

边缘/MoE 推理实证：OLMoE-1B-7B 在 Jetson Orin Nano 上比同 active 参数量 Dense 模型慢 31%，能耗高 2.1 倍；边缘带宽受限硬件上推理成本跟随总参数而非激活参数

MoE Edge Inference LLM Inference Hardware Benchmark Empirical Study

Kimi K3: Open Frontier Intelligence

2.8T 参数原生多模态 MoE、104B 激活参数、1M token 上下文、Kimi Delta Attention + Attention Residuals + Stable LatentMoE 的开源前沿模型

MoE Long-Context Kimi-Delta-Attention Attention-Residuals Native-Vision Agentic-RL Muon-Optimizer MXFP4-Quantization Kimi