Tian Tang

~Tian_Tang1

2

论文总数

2.0

年均投稿

6.9

平均评分

接收情况2/2

会议分布

ICLR

1

NeurIPS

1

发表论文 (2 篇)

20252 篇

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

ICLR 2025Poster

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning

NeurIPS 2025Spotlight

合作者 (12)

Baris Kasikci1 篇

Keisuke Kamahori1 篇

Chaofan Lin1 篇

Hanshuo Wang1 篇

Ion Stoica1 篇