Rohan Paul· @rohanpaul_ai · X·· 4 小时前AI 评分37
AI 导读
– https://arxiv.org/abs/2610.38981 标题:“为什么投机解码在稀疏MoE模型上的表现优于预期”
正文
– https://arxiv.org/abs/2610.38981
Title: "Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models"
来源:Rohan Paul · x.com