ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2410.12247
  4. Cited By
EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference

16 October 2024
Yulei Qian
Fengcun Li
Xiangyang Ji
Xiaoyu Zhao
Jianchao Tan
K. Zhang
Xunliang Cai
    MoE
ArXivPDFHTML

Papers citing "EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference"

1 / 1 papers shown
Title
Speculative MoE: Communication Efficient Parallel MoE Inference with Speculative Token and Expert Pre-scheduling
Speculative MoE: Communication Efficient Parallel MoE Inference with Speculative Token and Expert Pre-scheduling
Yan Li
Pengfei Zheng
Shuang Chen
Zewei Xu
Yuanhao Lai
Yunfei Du
Z. Wang
MoE
52
0
0
06 Mar 2025
1