500AI
Search

Song Han

  • Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
  • Once-for-All: Train One Network and Specialize it for Efficient Deployment
  • SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
  • Efficient Streaming Language Models with Attention Sinks

All names