Skip to content

Instantly share code, notes, and snippets.

@jaidevd
Created January 15, 2026 06:25
Show Gist options
  • Select an option

  • Save jaidevd/eb9ec14e8fe40a1b51aab7d98ba6f1f0 to your computer and use it in GitHub Desktop.

Select an option

Save jaidevd/eb9ec14e8fe40a1b51aab7d98ba6f1f0 to your computer and use it in GitHub Desktop.
Optimizing Torch Models - PyConf Hyd 2026

Talk Details

Title

Optimizing PyTorch Models

Elevator Pitch - 300 chars

Most AI models never leave a Jupyter notebook. This workshop shows how to turn real-world PyTorch codebases into deployable, efficient binaries—covering practical techniques for optimizing and exporting complex models to production at low cost.

Description - for attendees

Other than building and training deep neural networks, PyTorch offers a host of other tools to help optimize and export models, especially to lower-level frameworks and runtimes for deployment on edge devices. This workshop focuses on techniques which ensure that torch models (instances of torch.nn.Module) work well with frameworks like CoreML, TensorRT, and ONNX Runtime.

For most neural network architectures that are already present in the torch ecosystem (torch, torchvision, torchaudio, etc), optimization, compiling and export is usually not a significant problem. They're well supported by the community and are thus amenable to optimization. However, when it comes to SoTA models that typically beat an ML benchmark and are inspired by research papers, there is no guarantee that the code accompanying the papers will be suitable for deployment or even optimization. This is not all that surprising, since most code that is released alongside papers is meant primarily to reproduce the benchmarks that are in the paper. Portability and consumption is typically not a priority.

In this workshop, we will introduce a collection of recipes which we have developed by working with various SoTA models and making them work on edge devices, especially with torch. We will interactively cover a few SoTA architectures for computer vision tasks and develop a guidebook for how best to optimize and export torch models.

Notes - for reviewers

This is meant to be a fully hands-on workshop, meaning that the speaker's talking will be intersperesed with both the speaker and the audience coding. Participants will have to bring their own computers, or share them with others. A detailed Github repository will be made available to the participants closer to the workshop dates so that they can come prepared with the necessary tools and dependencies installed.


Profile Details

Name

Jaidev Deshpande

URL

https://jaidevd.com

Organization or Affiliation

  1. Aftershoot
  2. IIT Madras

Twitter Handle

jaidevd

Shirt Size

Men's M

Bio

Jaidev currently does MLOps at Aftershoot. He has a decade of experience in machine learning and software development. You are likely to run into him at various tech events.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment