Zeyu Mi

yzmizeyu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 12 months ago

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Paper • 2406.05955 • Published Jun 10, 2024 • 28

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Paper • 2406.06282 • Published Jun 10, 2024 • 39

upvoted a paper over 1 year ago

PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU

Paper • 2312.12456 • Published Dec 16, 2023 • 44