Initial commit

.circleci/config.yml

+# Python CircleCI 2.0 configuration file
+#
+# Check https://circleci.com/docs/2.0/language-python/ for more details
+#
+# Adopted from
+# https://github.com/facebookresearch/detectron2/blob/master/.circleci/config.yml
+
+version: 2
+
+# -------------------------------------------------------------------------------------
+# Environments to run the jobs in
+# -------------------------------------------------------------------------------------
+cpu: &cpu
+  docker:
+    - image: circleci/python:3.7
+  resource_class: medium
+
+gpu: &gpu
+  environment:
+    CUDA_VERSION: "10.1"
+  machine:
+    image: ubuntu-1604-cuda-10.1:201909-23
+  resource_class: gpu.large
+
+# -------------------------------------------------------------------------------------
+# Re-usable commands
+# -------------------------------------------------------------------------------------
+setup_venv: &setup_venv
+  - run:
+      name: Setup Virtual Env
+      working_directory: ~/
+      command: |
+        python -m venv ~/venv
+        echo ". ~/venv/bin/activate" >> $BASH_ENV
+        . ~/venv/bin/activate
+        python --version
+        which python
+        which pip
+        pip install --upgrade pip
+
+install_dep: &install_dep
+  - run:
+      name: Install Dependencies
+      command: |
+        pip install --progress-bar off -r requirements-test.txt
+        python -c 'import torch; print("Torch version:", torch.__version__)'
+        python -m torch.utils.collect_env
+
+install_repo: &install_repo
+  - run:
+      name: Install Repository
+      command: |
+        python setup.py build develop
+
+run_unittests: &run_unittests
+  - run:
+      name: Run Unit Tests
+      command: |
+        pytest --junitxml=test-results/junit.xml --verbose
+
+run_flake8: &run_flake8
+  - run:
+      name: Run Linter (flake8)
+      command: |
+        flake8 --show-source --statistics
+
+run_transformer_benchmark: &run_transformer_benchmark
+  - run:
+      name: Run Transformer Benchmark
+      command: |
+        python benchmarks/transformer.py
+
+# -------------------------------------------------------------------------------------
+# Jobs to run
+# -------------------------------------------------------------------------------------
+
+jobs:
+  cpu_tests:
+    <<: *cpu
+
+    working_directory: ~/fairscale
+
+    steps:
+      - checkout
+      - <<: *setup_venv
+
+      # Cache the venv directory that contains dependencies
+      - restore_cache:
+          keys:
+            - cache-key-cpu-{{ checksum "setup.py"}}-{{ checksum "requirements-test.txt"}}
+
+      - <<: *install_dep
+
+      - save_cache:
+          paths:
+            - ~/venv
+          key: cache-key-cpu-{{ checksum "setup.py"}}-{{ checksum "requirements-test.txt"}}
+
+      - <<: *install_repo
+
+      - run:
+          name: Run Linter (isort)
+          command: |
+            isort --check-only
+
+      - run:
+          name: Run Linter (black)
+          command: |
+            black --check .
+
+      - run:
+          name: Run type-checking (mypy)
+          command: |
+            mypy --pretty .
+
+      - <<: *run_flake8
+
+      - <<: *run_unittests
+
+      - store_test_results:
+          path: test-results
+
+  gpu_tests:
+    <<: *gpu
+
+    working_directory: ~/fairscale
+
+    steps:
+      - checkout
+
+      - run: nvidia-smi
+
+      - run: pyenv global 3.7.0
+
+      - <<: *setup_venv
+
+      # Cache the venv directory that contains dependencies
+      - restore_cache:
+          keys:
+            - cache-key-gpu-{{ checksum "setup.py"}}-{{ checksum "requirements-test.txt"}}
+
+      - <<: *install_dep
+
+      - save_cache:
+          paths:
+            - ~/venv
+          key: cache-key-gpu-{{ checksum "setup.py"}}-{{ checksum "requirements-test.txt"}}
+
+      - <<: *install_repo
+
+      - <<: *run_unittests
+
+      - store_test_results:
+          path: test-results
+
+  benchmarks:
+    <<: *gpu
+
+    working_directory: ~/fairscale
+
+    steps:
+      - checkout
+
+      - run: nvidia-smi
+
+      - run: pyenv global 3.7.0
+
+      - <<: *setup_venv
+
+      # Cache the venv directory that contains dependencies
+      - restore_cache:
+          keys:
+            - cache-key-gpu-{{ checksum "setup.py"}}-{{ checksum "requirements-test.txt"}}
+
+      - <<: *install_dep
+
+      - save_cache:
+          paths:
+            - ~/venv
+          key: cache-key-gpu-{{ checksum "setup.py"}}-{{ checksum "requirements-test.txt"}}
+
+      - <<: *install_repo
+
+      - <<: *run_transformer_benchmark
+
+
+workflows:
+  version: 2
+  build:
+    jobs:
+      - cpu_tests
+      - gpu_tests
+      - benchmarks

.editorconfig

+root = true
+
+[*.py]
+charset = utf-8
+trim_trailing_whitespace = true
+end_of_line = lf
+insert_final_newline = true
+indent_style = space
+indent_size = 4
+
+[*.md]
+trim_trailing_whitespace = false

.github/ISSUE_TEMPLATE/bug-report.md

+---
+name: "\U0001F41B Bug Report"
+about: Submit a bug report to help us improve fairscale
+
+---
+
+## 🐛 Bug
+
+<!-- A clear and concise description of what the bug is. -->
+
+## Command
+
+## To Reproduce
+
+Steps to reproduce the behavior:
+
+<!-- If you were running a command, post the exact command that you were running -->
+
+1.
+2.
+3.
+
+<!-- If you have a code sample, error messages, stack traces, please provide it here as well -->
+
+## Expected behavior
+
+<!-- A clear and concise description of what you expected to happen. -->
+
+## Environment
+
+Please copy and paste the output from the
+environment collection script from PyTorch
+(or fill out the checklist below manually).
+
+You can run the script with:
+```
+# For security purposes, please check the contents of collect_env.py before running it.
+python -m torch.utils.collect_env
+```
+
+ - PyTorch Version (e.g., 1.0):
+ - OS (e.g., Linux):
+ - How you installed PyTorch (`conda`, `pip`, source):
+ - Build command you used (if compiling from source):
+ - Python version:
+ - CUDA/cuDNN version:
+ - GPU models and configuration:
+ - Any other relevant information:
+
+## Additional context
+
+<!-- Add any other context about the problem here. -->

.github/ISSUE_TEMPLATE/feature-request.md

+---
+name: "\U0001F680Feature Request"
+about: Submit a proposal/request for a new fairscale feature
+
+---
+
+## 🚀 Feature
+<!-- A clear and concise description of the feature proposal -->
+
+## Motivation
+
+<!-- Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too -->
+
+## Pitch
+
+<!-- A clear and concise description of what you want to happen. -->
+
+## Alternatives
+
+<!-- A clear and concise description of any alternative solutions or features you've considered, if any. -->
+
+## Additional context
+
+<!-- Add any other context or screenshots about the feature request here. -->

.github/ISSUE_TEMPLATE/questions-help-support.md

+---
+name: "❓Questions/Help/Support"
+about: Do you need support?
+
+---
+
+## ❓ Questions and Help

.github/PULL_REQUEST_TEMPLATE.md

+# Before submitting
+
+- [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements)
+- [ ] Did you read the [contributor guideline](https://github.com/facebookresearch/fairscale/blob/master/CONTRIBUTING.md)?
+- [ ] Did you make sure to update the docs?
+- [ ] Did you write any new necessary tests?
+
+## What does this PR do?
+Fixes # (issue).
+
+## PR review
+Anyone in the community is free to review the PR once the tests have passed.
+If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
+
+## Did you have fun?
+Make sure you had fun coding 🙃

.gitignore

+*~
+*.pyc
+.mypy_cache/
+*.egg-info/

.isort.cfg

+[settings]
+known_third_party =models,pytest,setuptools,torch,torchtext

.pre-commit-config.yaml

+exclude: 'build|stubs'
+
+default_language_version:
+    python: python3
+
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.5.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: check-ast
+    -   id: check-merge-conflict
+    -   id: no-commit-to-branch
+        args: ['--branch=master']
+    -   id: check-added-large-files
+        args: ['--maxkb=500']
+    -   id: end-of-file-fixer
+
+-   repo: https://github.com/ambv/black
+    rev: stable
+    hooks:
+    - id: black
+      language_version: python3.6
+
+-   repo: https://gitlab.com/pycqa/flake8
+    rev: 3.7.9
+    hooks:
+    -   id: flake8
+
+-   repo: https://github.com/asottile/seed-isort-config
+    rev: v2.1.0
+    hooks:
+    -   id: seed-isort-config
+        language_version: python3.6
+
+-   repo: https://github.com/timothycrosley/isort
+    rev: 4.3.20
+    hooks:
+    -   id: isort
+        additional_dependencies: [toml]
+
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v0.770'
+    hooks:
+    -   id: mypy

CODE_OF_CONDUCT.md

+# Open Source Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others’ private information, such as a physical or electronic address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies within all project spaces, and it also applies when an individual is representing the project or its community in public spaces. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event. Representation of a project may be further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by contacting the project team at opensource-conduct@fb.com. All complaints will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. The project team is obligated to maintain confidentiality with regard to the reporter of an incident. Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good faith may face temporary or permanent repercussions as determined by other members of the project’s leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org

CONTRIBUTING.md

+# Contributing to fairscale
+We want to make contributing to this project as easy and transparent as
+possible.
+
+## Our Development Process
+Minor changes and improvements will be released on an ongoing basis. Larger changes (e.g., changesets implementing a new paper) will be released on a more periodic basis.
+
+## Pull Requests
+We actively welcome your pull requests.
+
+1. Fork the repo and create your branch from `master`.
+2. If you've added code that should be tested, add tests.
+3. If you've changed APIs, update the documentation.
+4. Ensure the test suite passes.
+5. Make sure your code lints.
+6. If you haven't already, complete the Contributor License Agreement ("CLA").
+
+## Contributor License Agreement ("CLA")
+In order to accept your pull request, we need you to submit a CLA. You only need
+to do this once to work on any of Facebook's open source projects.
+
+Complete your CLA here: <https://code.facebook.com/cla>
+
+## Issues
+We use GitHub issues to track public bugs. Please ensure your description is
+clear and has sufficient instructions to be able to reproduce the issue.
+
+Facebook has a [bounty program](https://www.facebook.com/whitehat/) for the safe
+disclosure of security bugs. In those cases, please go through the process
+outlined on that page and do not file a public issue.
+
+## Coding Style
+* In your editor, install the [editorconfig](https://editorconfig.org/) extension which should ensure that you are following the same standards as us.
+* Ideally, run black and isort before opening up your PR.
+
+```
+black ./(mmf|tests|tools)/**/*.py
+isort -rc (mmf|tests|tools)
+```
+* Read the [editorconfig](.editorconfig) file to understand the exact coding style preferences.
+
+## Commit Guidelines
+
+We follow the same guidelines as AngularJS. Each commit message consists of a **header**, a **body** and a **footer**.  The header has a special format that includes a **type**, and a **subject**:
+
+```
+[<type>] <subject>
+<BLANK LINE>
+<body>
+<BLANK LINE>
+<footer>
+```
+
+Any line of the commit message cannot be longer 100 characters! This allows the message to be easier
+to read on github as well as in various git tools.
+
+### Type
+Must be one of the following:
+
+* **feat**: A new feature
+* **fix**: A bug fix
+* **cleanup**: Changes that do not affect the meaning of the code (white-space, formatting, missing
+  semi-colons, dead code removal etc.)
+* **refactor**: A code change that neither fixes a bug or adds a feature
+* **perf**: A code change that improves performance
+* **test**: Adding missing tests or fixing them
+* **chore**: Changes to the build process or auxiliary tools and libraries such as documentation
+generation
+* **docs**: Documentation only changes
+
+## License
+By contributing to fairscale, you agree that your contributions will be licensed
+under the LICENSE file in the root directory of this source tree.

LICENSE

+From fairscale:
+
+Copyright (c) Facebook, Inc. and its affiliates
+
+===
+
+From torchgpipe (fairscale/nn/pipe):
+
+Copyright 2019 Kakao Brain
+
+All contributions by Facebook:
+Copyright (c) Facebook, Inc. and its affiliates
+
+===
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+3. Neither the names of Facebook, Deepmind Technologies, NYU, NEC Laboratories America
+   and IDIAP Research Institute nor the names of its contributors may be
+   used to endorse or promote products derived from this software without
+   specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.

NOTICE

+===============================================================================
+torchgpipe's Apache License 2.0
+===============================================================================
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2019 Kakao Brain
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

+# fairscale
+fairscale is a PyTorch extension library for high performance and large scale training.
+
+fairscale supports:
+* pipeline parallelism (fairscale.nn.Pipe)
+* optimizer state sharding (fairscale.optim.oss)
+
+## Examples
+
+Run a 4-layer model on 2 GPUs. The first two layers run on cuda:0 and the next two layers run on cuda:1.
+
+```bash
+import torch
+
+import fairscale
+
+model = torch.nn.Sequential(a, b, c, d)
+model = fairscale.nn.Pipe(model, balance=[2, 2], devices=[0, 1], chunks=8)
+```
+
+## Requirements
+
+* PyTorch >= 1.4
+
+## Installation
+
+Normal installation:
+```bash
+pip install .
+```
+
+Development mode:
+```bash
+pip install -e .
+```
+
+## Contributors
+
+See the [CONTRIBUTING](CONTRIBUTING.md) file for how to help out.
+
+## License
+
+fairscale is licensed under the [BSD-3-Clause License](LICENSE).

benchmarks/models/transformerModel.py

+# Copyright (c) Facebook, Inc. and its affiliates. All rights reserved.
+
+import math
+
+import torch
+import torch.nn as nn
+
+
+class TransformerModel(nn.Module):
+    def __init__(self, ntoken, ninp=200, nhead=2, nhid=200, nlayers=2, dropout=0.5):
+        super(TransformerModel, self).__init__()
+        from torch.nn import TransformerEncoder, TransformerEncoderLayer
+
+        self.model_type = "Transformer"
+        self.src_mask = None
+        self.pos_encoder = PositionalEncoding(ninp, dropout)
+        encoder_layers = TransformerEncoderLayer(ninp, nhead, nhid, dropout)
+        self.transformer_encoder = TransformerEncoder(encoder_layers, nlayers)
+        self.encoder = nn.Embedding(ntoken, ninp)
+        self.ninp = ninp
+        self.decoder = nn.Linear(ninp, ntoken)
+
+        self.init_weights()
+
+    def _generate_square_subsequent_mask(self, sz):
+        mask = (torch.triu(torch.ones(sz, sz)) == 1).transpose(0, 1)
+        mask = mask.float().masked_fill(mask == 0, float("-inf")).masked_fill(mask == 1, float(0.0))
+        return mask
+
+    def init_weights(self):
+        initrange = 0.1
+        self.encoder.weight.data.uniform_(-initrange, initrange)
+        self.decoder.bias.data.zero_()
+        self.decoder.weight.data.uniform_(-initrange, initrange)
+
+    def forward(self, src):
+        if self.src_mask is None or self.src_mask.size(0) != len(src):
+            device = src.device
+            mask = self._generate_square_subsequent_mask(len(src)).to(device)
+            self.src_mask = mask
+
+        src = self.encoder(src) * math.sqrt(self.ninp)
+        src = self.pos_encoder(src)
+        output = self.transformer_encoder(src, self.src_mask)
+        output = self.decoder(output)
+        return output
+
+
+class PositionalEncoding(nn.Module):
+    def __init__(self, d_model, dropout=0.1, max_len=5000):
+        super(PositionalEncoding, self).__init__()
+        self.dropout = nn.Dropout(p=dropout)
+
+        pe = torch.zeros(max_len, d_model)
+        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
+        div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
+        pe[:, 0::2] = torch.sin(position * div_term)
+        pe[:, 1::2] = torch.cos(position * div_term)
+        pe = pe.unsqueeze(0).transpose(0, 1)
+        self.register_buffer("pe", pe)
+
+    def forward(self, x):
+        x = x + self.pe[: x.size(0), :]
+        return self.dropout(x)

benchmarks/transformer.py

+# Copyright (c) Facebook, Inc. and its affiliates. All rights reserved.
+
+import math
+import time
+
+from models import transformerModel as transformer
+import torch
+import torch.nn as nn
+import torchtext
+from torchtext.data.utils import get_tokenizer
+
+
+def get_data(device):
+    TEXT = torchtext.data.Field(
+        tokenize=get_tokenizer("basic_english"), init_token="<sos>", eos_token="<eos>", lower=True
+    )
+    train_txt, val_txt, test_txt = torchtext.datasets.WikiText2.splits(TEXT)
+    TEXT.build_vocab(train_txt)
+    ntokens = len(TEXT.vocab.stoi)
+
+    batch_size = 20
+    eval_batch_size = 10
+    train_data = batchify(train_txt, batch_size, TEXT, device)
+    val_data = batchify(val_txt, eval_batch_size, TEXT, device)
+    test_data = batchify(test_txt, eval_batch_size, TEXT, device)
+
+    return ntokens, train_data, val_data, test_data
+
+
+def batchify(data, bsz, TEXT, device):
+    data = TEXT.numericalize([data.examples[0].text])
+    nbatch = data.size(0) // bsz
+    data = data.narrow(0, 0, nbatch * bsz)
+    data = data.view(bsz, -1).t().contiguous()
+    return data.to(device)
+
+
+def get_batch(source, i, bptt):
+    seq_len = min(bptt, len(source) - 1 - i)
+    data = source[i : i + seq_len]
+    target = source[i + 1 : i + 1 + seq_len].view(-1)
+    return data, target
+
+
+def make_model(device, ntokens):
+    emsize = 50  # embedding dimension
+    nhid = 50  # the dimension of the feedforward network model in nn.TransformerEncoder
+    nlayers = 1  # the number of nn.TransformerEncoderLayer in nn.TransformerEncoder
+    nhead = 2  # the number of heads in the multiheadattention models
+    dropout = 0.2  # the dropout value
+    model = transformer.TransformerModel(ntokens, emsize, nhead, nhid, nlayers, dropout).to(device)
+    criterion = nn.CrossEntropyLoss()
+    lr = 5.0  # learning rate
+    optimizer = torch.optim.SGD(model.parameters(), lr=lr)
+
+    return model, criterion, optimizer
+
+
+def train(train_data, model, criterion, optimizer, bptt, ntokens):
+    model.train()
+    total_loss = 0.0
+    start_time = time.time()
+    for batch, i in enumerate(range(0, train_data.size(0) - 1, bptt)):
+        data, targets = get_batch(train_data, i, bptt)
+        optimizer.zero_grad()
+        output = model(data)
+        loss = criterion(output.view(-1, ntokens), targets)
+        loss.backward()
+        torch.nn.utils.clip_grad_norm_(model.parameters(), 0.5)
+        optimizer.step()
+
+        total_loss += loss.item()
+        log_interval = 200
+        if batch % log_interval == 0 and batch > 0:
+            cur_loss = total_loss / log_interval
+            elapsed = time.time() - start_time
+            print(
+                "| {:5d}/{:5d} batches | ms/batch {:5.2f} | loss {:5.2f} | ppl {:8.2f}".format(
+                    batch, len(train_data) // bptt, elapsed * 1000 / log_interval, cur_loss, math.exp(cur_loss),
+                )
+            )
+            total_loss = 0
+            start_time = time.time()
+
+
+def evaluate(eval_model, data_source, criterion, bptt, ntokens):
+    eval_model.eval()
+    total_loss = 0.0
+    with torch.no_grad():
+        for i in range(0, data_source.size(0) - 1, bptt):
+            data, targets = get_batch(data_source, i, bptt)
+            output = eval_model(data)
+            output_flat = output.view(-1, ntokens)
+            total_loss += len(data) * criterion(output_flat, targets).item()
+    return total_loss / (len(data_source) - 1)
+
+
+def get_number_of_words(data):
+    return data.size()[0] * data.size()[1]
+
+
+def benchmark_language_model(train_data, val_data, test_data, model, criterion, optimizer, ntokens):
+    epoch = 1
+    bptt = 35
+    start_time = time.time()
+
+    print("-" * 89)
+    print("| start of epoch {:1d}".format(epoch))
+    print("-" * 89)
+    epoch_start_time = time.time()
+    train(train_data, model, criterion, optimizer, bptt, ntokens)
+    val_loss = evaluate(model, val_data, criterion, bptt, ntokens)
+    print("-" * 89)
+    print(
+        "| end of epoch {:1d} | time: {:5.2f}s | valid loss {:5.2f} | "
+        "valid ppl {:8.2f}".format(epoch, (time.time() - epoch_start_time), val_loss, math.exp(val_loss))
+    )
+    print("-" * 89)
+
+    elapsed_time = time.time() - start_time
+    nwords = get_number_of_words(train_data) + get_number_of_words(val_data)
+    wps = nwords / elapsed_time
+
+    test_loss = evaluate(model, test_data, criterion, bptt, ntokens)
+    print("=" * 89)
+    print(
+        "| end of training | test loss {:5.2f} | test ppl {:8.2f}\n| time: {:5.2f}s | words: {:3d} | wps: {:5.2f}".format(
+            test_loss, math.exp(test_loss), elapsed_time, nwords, wps
+        )
+    )
+    print("=" * 89)
+
+
+if __name__ == "__main__":
+    assert torch.cuda.is_available()
+    device = torch.device("cuda")
+    ntokens, train_data, val_data, test_data = get_data(device)
+    model, criterion, optimizer = make_model(device, ntokens)
+    benchmark_language_model(train_data, val_data, test_data, model, criterion, optimizer, ntokens)

fairscale/__init__.py

+# Copyright (c) Facebook, Inc. and its affiliates. All rights reserved.
+#
+# This source code is licensed under the BSD license found in the
+# LICENSE file in the root directory of this source tree.
+
+################################################################################
+# Import most common subpackages
+################################################################################
+
+from . import nn

fairscale/nn/__init__.py

+from .pipe import Pipe
+
+__all__ = ["Pipe"]

fairscale/nn/pipe/__init__.py

+# Copyright (c) Facebook, Inc. and its affiliates. All rights reserved.
+#
+# This source code is licensed under the BSD license found in the
+# LICENSE file in the root directory of this source tree.
+
+# Copyright 2019 Kakao Brain
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""A Pipe implementation in PyTorch."""
+from .checkpoint import is_checkpointing, is_recomputing
+from .pipe import Pipe
+
+__all__ = ["Pipe", "is_checkpointing", "is_recomputing"]