Hacker NewsSep 21

I Parallelized RNN Training from O(T) to O(log T) Using CUDA

https://dhruvmsheth.github.io/projects/gpu_pogramming_curnn/

#HackerNews #ParallelizedRNN #CUDA #Training #O(logT) #MachineLearning #DeepLearning #GPUProgramming

Were RNNs All We Needed? A GPU Programming Perspective | Dhruv Sheth

An implementation of parallelizable GRUs and LSTMs for CS179 in CUDA.