torchlambda is a tool to deploy PyTorch models on Amazon's AWS Lambda using AWS SDK for C++ and custom C++ runtime.

Using statically compiled dependencies whole package is shrunk to only 30MB.

Due to small size of compiled source code users can pass their models as AWS Lambda layers. Services like Amazon S3 are no longer necessary to load your model.

torchlambda has it's PyTorch & AWS dependencies always up to date because of continuous deployment run at 03:00 a.m. every day.

Docs Deployment Package Python PyTorch Docker CodeBeat Images
Documentation CD PyPI Python PyTorch Docker codebeat badge Images

Comparison with other deployment tools

  • Do one thing and do it well - most deployment tools are complex solutions including multiple frameworks and multiple services. torchlambda focuses solely on PyTorch and AWS Lambda integration.
  • Write programs to work together - Amazon AWS tools exist for a reason, no need to repeat their functionalities (like aws-cli) or interfere with your PyTorch source code.
  • Small is beautiful - 3000 LOC where most of it are Python argument parsing from user makes it relatively easy to delve into source code and modify on your own.
  • Focus on lightweight inference - you can't train you neural network with torchlambda. There are other tools for that and should be used when appropriate.
  • Easy to jump in - no need to learn new tool. torchlambda has at most 4 commands simplifying steps to take PyTorch model into the cloud.
  • Extensible when you need it - No additional source code needed (except YAML settings), but fully possible if you need it. You can also tune PyTorch and AWS SDK dependencies for your specific use-case

Table Of Contents

Footnotes

1. Support for latest version of it's main DL framework or main frameworks if multiple supported

2. Project dependencies are easily customizable. In torchlambda it would be user specified build procedures for libtorch and AWS C++ SDK

3. Necessary size of code and dependencies to deploy model

4. Based on Dockerfile size

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (1602697918)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for szymonmaszke from gravatar.com szymonmaszke

Credits

Author: Szymon Maszke

License

MIT License (MIT)

Requires

Python >=3.6

Tags

aws lambda pytorch deployment minimal c++ neural network model

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

torchlambda-1587188625.tar.gz (21.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

torchlambda-1587188625-py3-none-any.whl (28.7 kB view details)

Uploaded Python 3

File details

Details for the file torchlambda-1587188625.tar.gz.

File metadata

  • Download URL: torchlambda-1587188625.tar.gz
  • Upload date:
  • Size: 21.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.1.3 requests-toolbelt/0.9.1 tqdm/4.45.0 CPython/3.7.7

File hashes

Hashes for torchlambda-1587188625.tar.gz
Algorithm Hash digest
SHA256 45e98241e21a7bfa2db04e1c3c3bfa070a7efa0191c2209dd46ebf511eefd325
MD5 a706ee4addea87ecc377143f8da55e63
BLAKE2b-256 97d7be684b343bb63107ac9bc32a50c6173470c69acb7307076683b104710d2a

See more details on using hashes here.

File details

Details for the file torchlambda-1587188625-py3-none-any.whl.

File metadata

  • Download URL: torchlambda-1587188625-py3-none-any.whl
  • Upload date:
  • Size: 28.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.1.3 requests-toolbelt/0.9.1 tqdm/4.45.0 CPython/3.7.7

File hashes

Hashes for torchlambda-1587188625-py3-none-any.whl
Algorithm Hash digest
SHA256 7defe452d47d4d72cac1b34c276a8b2493dc7131ff0465108c5e2a826947192e
MD5 5a0bda1035a41f807312af764c035b5c
BLAKE2b-256 ccb0485e84e9c4d71f81a8f3b65287befe73408ffaeef873bdd45b60176bbf03

See more details on using hashes here.

Release history Release notifications | RSS feed

1602697918

2 files

1601291906

2 files

1595906030

2 files

1595819652

2 files

1595733302

2 files

1595474049

2 files

1595387628

2 files

1595301221

2 files

1595214841

2 files

1595128522

2 files

1595041925

2 files

1594955646

2 files

1594869114

2 files

1594782747

2 files

1594696299

2 files

1594609980

2 files

1594523557

2 files

1594437091

2 files

1594350707

2 files

1594264306

2 files

1594177870

2 files

1594094149

2 files

1594005065

2 files

1593918755

2 files

1593832226

2 files

1593745839

2 files

1593659437

2 files

1593573080

2 files

1593486308

2 files

1593399935

2 files

1593313558

2 files

1593227076

2 files

1593140678

2 files

1593054270

2 files

1592967843

2 files

1592881427

2 files

1592795072

2 files

1592708716

2 files

1592622225

2 files

1592535849

2 files

1592449451

2 files

1592363000

2 files

1592276628

2 files

1592190229

2 files

1592103896

2 files

1592017417

2 files

1591931008

2 files

1591844533

2 files

1591758192

2 files

1591671785

2 files

1591585390

2 files

1591499021

2 files

1591412566

2 files

1591326285

2 files

1591239753

2 files

1591153498

2 files

1591066990

2 files

1591017093

2 files

1590990451

2 files

1590904228

2 files

1590817644

2 files

1590731191

2 files

1590644951

2 files

1590472189

2 files

1590385718

2 files

1590299449

2 files

1590212916

2 files

1590040004

2 files

1589867204

2 files

1589780740

2 files

1589694355

2 files

1589607984

2 files

1589521526

2 files

1589435214

2 files

1589348729

2 files

1589262226

2 files

1589175683

2 files

1589089467

2 files

1589003279

2 files

1588916857

2 files

1588830431

2 files

1588743886

2 files

1588657448

2 files

1588570997

2 files

1588484620

2 files

1588398086

2 files

1588311825

2 files

1588225513

2 files

1588052537

2 files

1587966020

2 files

1587793412

2 files

1587706841

2 files

1587447737

2 files

1587361328

2 files

This release

1587188625 This release

2 files

1587015624

2 files

1586929498

2 files

1586842928

2 files

1586317413

2 files

1586230943

2 files

1586030961

2 files

1585885600

2 files

1585813450

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page