jwfromm opened a new pull request #5975: URL: https://github.com/apache/incubator-tvm/pull/5975
This tutorial demonstrates how to load and run a sparse model from the popular transformers module from [Hugging Face](https://huggingface.co/) (🤗). Very recently a 95% sparse version of BERT was made publicly available however 🤗 was unable to achieve speedups using existing frameworks. Using this script, TVM enables a 2-3X speedup by converting appropriate dense layers to sparse dense layers. I think this will be a useful tutorial for user's interested in sparse networks and may be good PR for TVM as a small collaboration with 🤗. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
