"Activation Sequence Caching: High-Throughput and Memory-Efficient ..."

Sowoong Kim et al. (2024)

> Home

Details and statistics

DOI: 10.1145/3656019.3676945

access: closed

type: Conference or Workshop Paper

metadata version: 2024-10-22

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/IEEEpact/KimSSCB24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/IEEEpact/KimSSCB24
Sowoong Kim, Eunyeong Sim, Youngsam Shin, YeonGon Cho, Woongki Baek:
Activation Sequence Caching: High-Throughput and Memory-Efficient Generative Inference with a Single GPU. PACT 2024: 78-90

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.