latest | popular

Filter by
Fast Block Sparse Matrices for Pytorch
Enables networks which are both smaller and faster to let anybody use neural networks in production at low cost, and to improve the experience for the end ...
sparsity pytorch gpu efficiency
How We Scaled Bert To Serve 1+ Billion Daily Requests on CPUs
The nitty-gritty optimizations needed to get our Bert PyTorch models from our labs to productio.
bert cpu transformers efficiency
projects 1 - 2 of 2
Topic experts
Share a project
Share something you or the community has made with ML.