from Hacker News

Automating Optimization of Quantized Deep Learning Models on CUDA

by crowwork on 4/30/19, 6:21 PM with 2 comments

  • by junrushao1994 on 4/30/19, 7:25 PM

    Nice work accelerating convolutional models! It might be better to see (or cite papers about) the trade-off how model performance (accuracy, etc) changes w.r.t. how it is quantized.
  • by crowwork on 4/30/19, 6:22 PM

    With learning-based program optimizer, we can competitive performance on benchmark models and significant boost on emerging models against TensorRT(int8).