PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models(supercomputing-system-ai-lab.github.io)
supercomputing-system-ai-lab.github.io
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models
https://supercomputing-system-ai-lab.github.io/projects/puzzlemoe/
0 コメント
—