FastSeq provides efficient implementation of popular sequence models (e.g. Bart, ProphetNet) for text generation, summarization, translation tasks etc. It automatically optimizes inference speed based on popular NLP toolkits (e.g. FairSeq and HuggingFace-Transformers) without accuracy loss. All these can be easily done (no need to change any code/model/data if using our command line tool, or simply add one-line code import fastseq if using source code).

• EL-Attention: Memory Efficient Lossless Attention for Generation
• GPU-based Block N-Gram Repeats
• Asynchronous Pipeline for Postprocess

Below shows the generation speed gain by using FastSeq.

• All benchmarking experiments run on NVIDIA-V100-16GB with docker. Highest speed recorded for each model by tuning batch size. For parameter setting details, click link of corresponding model.
• The baseline (W/O Fastseq) for ProphetNet (fs) is run with fairseq 0.9.0, as it has not yet been updated for compatibility with version 0.10.2
• fs stands for Fairseq 0.10.2 version, hf stands for Huggingface Transformers 4.12.0 version.
• Optimizations were automatically applied to all generation/sequence models in Fairseq & Huggingface Transformers. Above only lists a subset of them.

FastSeq develops multiple speedup techniques, including an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O. These optimizations support various Transformer-based model architectures, such as the encoder-decoder architecture, the decoder-only architecture, and the encoder-only architecture. The more efficient implementations in FastSeq will be automatically patched to replace the ones in existing NLP toolkits (e.g., HuggingFace-Transformers and FairSeq), so there is no need of big code changes to integrate FastSeq with these toolkits.

• Python version >= 3.6
• torch >= 1.4.0
• fairseq >= 0.10.0
• transformers >= 4.12.0
• requests >= 2.24.0
• absl-py >= 0.9.0
• rouge-score >= 0.0.4

If you use fairseq or transformers, you only need to install one of them. If you use both, you need to install both.

The dockerfile requires the specification of a base image.

cd fastseq/docker
# pass the base image name as a build-arg when building the image from the dockerfile
docker build --build-arg BASE_IMAGE=nvcr.io/nvidia/pytorch:20.03-py3 .

# when fairseq and/or transformers has been installed
$ pip install git+https://github.com/microsoft/fastseq.git

# install fastseq + transformers
$ pip install git+https://github.com/microsoft/fastseq.git#egg=fastseq[transformers]

# install fastseq + fairseq
$ pip install git+https://github.com/microsoft/fastseq.git#egg=fastseq[fairseq]

# install fastseq + transformers + fairseq
$ pip install git+https://github.com/microsoft/fastseq.git#egg=fastseq[transformers,fairseq]

Only one line of code change is needed to use the optimizations provided by FastSeq.

# import fastseq at the beginning of your program
import fastseq
import torch

# Download bart.large.cnn
bart = torch.hub.load('pytorch/fairseq', 'bart.large.cnn')

bart.cuda()  # use GPU
bart.eval()  # disable dropout for evaluation
bart.half()

slines = ['FastSeq provides efficient implementations of the popular sequence models. Please visit https://github.com/microsoft/fastseq for more details.']

hypotheses = bart.sample(
    slines, beam=4, lenpen=2.0, max_len_b=140, min_len=55, no_repeat_ngram_size=3)

print(hypotheses)

Example usage for bart model on cnn daily mail task.

$ fastseq-generate-for-fairseq \
    cnn_dnn/bin \
    --path bart.large.cnn/model.pt \
    --fp16 \
    --task translation \
    --batch-size 128 \
    --gen-subset valid \
    --truncate-source  \
    --bpe gpt2 \
    --beam 4 \
    --num-workers 4 \
    --min-len 55 \
    --max-len-b 140 \
    --no-repeat-ngram-size 3 \
    --lenpen 2.0

Both model file and task data file are the same as original Fairseq version.

Example usage for bart model on cnn daily mail task.

$ fastseq-generate-for-transformers \
    facebook/bart-large-cnn \
    cnn_dm/val.source \
    out.summary \
    --reference_path cnn_dm/val.target \
    --device cuda \
    --bs 128 \
    --fp16 \
    --score_path out.score \
    --task summarization

Both model file and task data file are the same as original Transformers version.

# run a single test.
$ python tests/optimizer/fairseq/test_fairseq_optimizer.py

# run all the tests.
$ python -m unittest discover -s tests/ -p '*.py'

# run all the benchmarks.
$ cd benchmarks && bash run_all_benchmarks.sh

Changes to Python code should conform to PEP 8. yapf can be used to help format the python code, and use pylint to check your Python changes.

# format the code by yapf
$ yapf --style pep8 -i -r PYTHON_FILE/PACKAGE

# run pylint check
$ pylint --rcfile=.pylintrc  PYTHON_FILE/PACKAGE

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Please cite as:

@inproceedings{yan-etal-2021-fastseq,
    title = "{F}ast{S}eq: Make Sequence Generation Faster",
    author = "Yan, Yu and Hu, Fei and Chen, Jiusheng and Bhendawade, Nikhil and Ye, Ting and Gong, Yeyun  and Duan, Nan  and Cui, Desheng  and Chi, Bingyu and Zhang, Ruofei",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations",
    year = "2021",
}


@InProceedings{pmlr-v139-yan21a,
  title = 	 {EL-Attention: Memory Efficient Lossless Attention for Generation},
  author =       {Yan, Yu and Chen, Jiusheng and Qi, Weizhen and Bhendawade, Nikhil and Gong, Yeyun and Duan, Nan and Zhang, Ruofei},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {11648--11658},
  year = 	 {2021},
}