Counting 3,146 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Sep. 24, 2018
Aug. 28, 2017


SRU is a recurrent unit that can run over 10 times faster than cuDNN LSTM, without loss of accuracy tested on many tasks.

Average processing time of LSTM, conv2d and SRU, tested on GTX 1070

For example, the figure above presents the processing time of a single mini-batch of 32 samples. SRU achieves 10 to 16 times speed-up compared to LSTM, and operates as fast as (or faster than) word-level convolution using conv2d.


Simple Recurrent Units for Highly Parallelizable Recurrence

  title={Simple Recurrent Units for Highly Parallelizable Recurrence},
  author={Tao Lei, Yu Zhang, Sida I. Wang, Hui Dai and Yoav Artzi},
  booktitle={Empirical Methods in Natural Language Processing (EMNLP)},


Install requirements via pip install -r requirements.txt. CuPy and pynvrtc needed to support training / testing on GPU.


From source:

SRU can be installed as a regular package via python install or pip install ..

From PyPi:

pip install sru

Directly use the source without installation:

Make sure this repo and CUDA library can be found by the system, e.g.

export PYTHONPATH=path_to_repo/sru
export LD_LIBRARY_PATH=/usr/local/cuda/lib64


The usage of SRU is similar to nn.LSTM. SRU likely requires more stacking layers than LSTM. We recommend starting by 2 layers and use more if necessary (see our report for more experimental details).

import torch
from torch.autograd import Variable
from sru import SRU, SRUCell

# input has length 20, batch size 32 and dimension 128
x = Variable(torch.FloatTensor(20, 32, 128).cuda())

input_size, hidden_size = 128, 128

rnn = SRU(input_size, hidden_size,
    num_layers = 2,          # number of stacking RNN layers
    dropout = 0.0,           # dropout applied between RNN layers
    rnn_dropout = 0.0,       # variational dropout applied on linear transformation
    bidirectional = False,   # bidirectional RNN
    layer_norm = False,      # apply layer normalization on the output of each layer
    highway_bias = 0,        # initial bias of highway gate (<= 0)
    weight_norm = False,     # apply weight normalization on parameters (deprecated)
    rescale = True,          # whether to use scaling correction

output_states, c_states = rnn(x)      # forward pass

# output_states is (length, batch size, number of directions * hidden size)
# c_states is (layers, batch size, number of directions * hidden size)


Other Implementations

@musyoku had a very nice SRU implementaion in chainer.

@adrianbg implemented the first CPU version.

Latest Releases
sru 2.0.0
 Aug. 30 2018