Qingwei Ji
  • Bio
  • Publications
  • Blog
  • Blog
    • LLM推理论文精读2 -- PowerNPU[ASPLOS'25]
    • LLM推理论文精读1 -- FlexGen[ICML'23]
    • Transformer Model Learning
    • ElasticFlow: Serverless DDL Training is better?
    • Combinatorial Online Optimization For Online DML Job Scheduling
    • A Preemptive Scheduler for DML Jobs In Edge-Cloud·22'JSAC
    • A Deadline-Aware Scheduler for DLT Jobs·21'SoCC
    • Primal-Dual Approximate Algorithm Based On LP
    • Deep Learning Workloads Scheduling in GPU Clusters
    • How To Support Elastic Trainging
    • Online Scheduling of DML Jobs
  • Publications

LLM推理论文精读2 -- PowerNPU[ASPLOS'25]

Oct 15, 2024 · 0 min read
Last updated on Oct 15, 2024
LLM Inference Offloading Smartphone
Qingwei Ji
Authors
Qingwei Ji
CS Ph.D. Candidate @ SEU
LLM推理论文精读1 -- FlexGen[ICML'23] Oct 12, 2024 →

© {2024} Qingwei Ji. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.