mtszkw/fast-torch

Comparing PyTorch, JIT and ONNX for inference with Transformers

19
/ 100
Experimental

This project helps machine learning engineers and data scientists efficiently compare different methods for deploying PyTorch Transformer models for inference. It takes a pre-trained sentiment analysis model and test text sequences, then measures and compares prediction speeds using standard PyTorch, TorchScript, and ONNX Runtime. The output is a clear performance comparison, indicating the fastest inference method for a given model.

No commits in the last 6 months.

Use this if you need to quickly evaluate and choose the most performant deployment strategy for your PyTorch Transformer models to optimize prediction speed.

Not ideal if you are looking for a general-purpose model training or a detailed guide on model quantization or pruning.

MLOps model deployment inference optimization natural language processing performance benchmarking
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

20

Forks

1

Language

Python

License

Last pushed

Feb 22, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mtszkw/fast-torch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.