Coder Social home page Coder Social logo

kobart's People

Contributors

haven-jeon avatar seujung avatar

Watchers

 avatar

kobart's Issues

Request a feature to export KoBART for sequence classification to ONNX Runtime (ORT)

πŸš€ Feature request

  • I'd like to implement a feature to export KoBART to ONNX Runtime
  • Of course, transformers officially supports exporting to ONNX Runtime [here]
  • However, I found the dependency conflict below:
  1. SKT-AI/KoBART requires transformers==4.3.3
  2. transformers>=4.9.0 supports exporting BART to ONNX
  • I'd like to address this conflict to export KoBART to ONNX Runtime

Motivation

  • I'd like to optimize the computational resources of KoBART
  • The toolkits or frameworks I can choose:
  1. TensorRT (TRT)
  2. ONNX Runtime (ORT)
  3. OpenVINO
Highlights Which one is better or worse?
performance TRT β‰₯ ORT
ORT are sometimes on par with TRT
hardware TRT ≀ ORT
TRT only supports NVIDIA GPU
ORT supports NVIDIA GPU and Intel CPU
I cannot find any document about AMD for ORT πŸ™ˆ
compatibility TRT << ORT
TRT performs device-specific optimizations [1, 2]
For example, an execution engine built for a Nvidia A100 GPU will not work on a Nvidia T4 GPU πŸ™ƒ
difficulty TRT β‰₯ ORT
  • MichaΓ«l Benesty compares two methodologies, ORT and TRT
  • And transformers officially supports exporting to ONNX Runtime [here]

Your contribution

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.