Join CastLab
  • Home
  • Research
    • AI Accelerators
    • Multi-FPGA Systems
    • Processing-in-Memory
    • Near-Data Processing
  • People
    • Professor
    • Our Team
    • Alumni
  • Publications
    • Conference Papers
    • Journal Papers
    • Patents
    • Books
    • Open Source
  • Talks & Events
  • Awards
  • News
  • LINKEDIN
  • October 14, 2021
  • Comments off

“A Heterogeneous Vector-Array Architecture with Resource Scheduling for Multi-User/Multi-DNN Workloads” Architecture, Compiler, and System Support for Multi-model DNN Workloads (ACSMD) Workshop (MICRO Workshop), 2021

Paper Link: https://scontent.ficn2-2.fna.fbcdn.net/v/t39.8562-6/264678175_638181700547693_1020667141522086569_n.pdf?_nc_cat=106&ccb=1-6&_nc_sid=ad8a9d&_nc_ohc=0P4Do9N_VNEAX9wOvd8&_nc_ht=scontent.ficn2-2.fna&oh=00_AT87Z_o7_qAQ3WSO4GSsYM2uHTuzprjDtKzYuzRpHiwevg&oe=627F6F18

Post navigation

Previous post
Next post

Recent Posts

April 02, 2025

[VLSI 2025] Jung-Hoon Kim’s paper on Adelia: A 4nm LLM Accelerator with Streamlined Dataflow and Dual-Mode Parallelization for Efficient Generative AI Inference is accepted

March 24, 2025

[ISCA 2025] Seungjae Moon and Junseo Cha’s paper on Hybe: GPU-NPU Hybrid System for Efficient LLM Inference with Million-Token Context Window is accepted

March 24, 2025

[ISCA 2025] Sungmin Hong’s paper on Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization is accepted

Address: #4209, School of Electrical Engineering (E3-2), KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, South Korea     Tel: +82-42-350-7461     Email: castlab@kaist.ac.kr

Copyright© 2019 - CastLab