Initial 0.1.0 Release of FastNN
A small release for a fun little project with more to come.
For this initial release you can refer to the README and at https://andrewchang.dev/fastnn
But here are some of the features this includes:
- Data Processing
- Intuitive data processing modules for encoding human-readible data into tensors compatible with deep learning libraries
- Model Exporting
- FastNN torch modules and tools for exporting models via.
TorchScript
tracing and scripting to a production environment
- FastNN torch modules and tools for exporting models via.
- Model Zoo
- Various exported models hosted in this repo via. git-lfs and AWS S3. Includes models from the HuggingFace's Transformers and
TorchVision
- Various exported models hosted in this repo via. git-lfs and AWS S3. Includes models from the HuggingFace's Transformers and
- Model Deployment
- Deploy models using Triton Inference Server on CPU/GPU-compatible server(s) with helm or docker
- FastNN Client
- Client wrapper for Triton Inference Server's client module for programmatic requests with python