"RoPE on the Fast Track: Latency-Optimized LLM Inference on GPUs with ..."

Gilhyeon Lee et al. (2025)

> Home

Details and statistics

DOI: 10.1109/APCCAS67402.2025.11378253

access: closed

type: Conference or Workshop Paper

metadata version: 2026-05-19

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/apccas/LeeJGK25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/apccas/LeeJGK25
Gilhyeon Lee, Jihoon Jang, Kyungmin Goh, Hyun Kim:
RoPE on the Fast Track: Latency-Optimized LLM Inference on GPUs with Low-Rank QKV Factorization and Rotary Positional Embedding. APCCAS 2025: 1-5

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.