Machine Learning

Block-Sparse GPU Kernels

Tagged: ,

This topic contains 0 replies, has 1 voice, and was last updated by  OpenAi 1 year ago.

  • Block-Sparse GPU Kernels

    We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights. Depending on the chosen sparsity, these kernels can run orders of magnitude faster than cuBLAS or cuSPARSE. We’ve used them to attain state-of-the-art results in text sentiment analysis and generative modeling of

    Block-Sparse GPU Kernels
    by OpenAI

You must be logged in to reply to this topic.