MLOps Conference
The Fifth Elephant
The Fifth Elephant

MLOps Conference

On DataOps, productionizing ML models, and running experiments at scale.

Tickets

Loading…

All submissions
This submission has been added to the schedule

Pratik Bhavsar

@nlpguy

End2End Serverless Transformers On AWS Lambda For NLP

Submitted Jun 27, 2021

Transformers are everywhere! But how to serve them? How do you leverage serverless to get scalability without any worries? Isn’t serverless used for light applications?. How to get the best latencies with your serverless? I will be sharing answers to these questions in my talk.

Slides - https://bit.ly/serverless-transformers

About Pratik

A self-taught data scientist and open-source developer from India. He specialises in making Search & NLP solutions.
He runs a slack data science community http://maxpool.club and writes at https://pakodas.substack.com.
You can find his previous talks with PyData, WiMLDS & DAIR at http://talks.pratik.ai
Portfolio - http://pratik.ai

Agenda

  1. Paradigms of deployment
    • Live server
    • Batch processing
    • Serverless
  2. Benefits of serverless
  3. Deploying transformer models on Lambda
  4. Exposing API
  5. Versioning lambdas
  6. CI/CD with GitHub actions
  7. Runtime limitations and consequences
  8. Multi-tenant design for lambdas
  9. Conclusion

Key takeaways

Learn to deploy transformers in production
Serverless can be really good for many scenarios
Get huge instant scalability with serverless
Tons of savings in cost and headache

Audience

Any level of audience and whole ML community

All submissions

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hybrid access (members only)

Hosted by

The Fifth Elephant
The Fifth Elephant
Jump starting better data engineering and AI futures

Supported by

Scribble Data
Scribble Data
Scribble Data builds feature stores for data science teams that are serious about putting models (ML, or even sub-ML) into production. The ability to systematically transform data is the single biggest determinant of how well these models do. Scribble Data streamlines the feature engineering proces… more

Promoted

Privacy Mode
Privacy Mode
Deep dives into privacy and security, and understanding needs of the Indian tech ecosystem through guides, research, collaboration, events and conferences. Sponsors: Privacy Mode’s programmes are sponsored by: more