Rotary GPU: Exploring Local Execution for Large MoE Models Under Limited VRAM
Abstract page for arXiv paper 2605.29135: Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory
Read full article →Abstract page for arXiv paper 2605.29135: Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory
Read full article →