Fastnn

What's Changed
* Update dependencies and add text generation by aychang95 in https://github.com/aychang95/fastnn/pull/9
* fix python version by aychang95 in https://github.com/aychang95/fastnn/pull/10

Added text generation

**Full Changelog**: https://github.com/aychang95/fastnn/compare/v0.3.0...0.4.0

Major dependency updates.

Official support python3.7.10-3.11.

Added `sentence-transformers` as dependency

**Full Changelog**: https://github.com/aychang95/fastnn/compare/0.2.0...v0.3.0

Haven't released in a while.

Update and organize dependencies within extras. FastNN main dependencies are transformers, pytorch, and triton client.

Update documentation and replace mkautodocs(archive-mode) with mkdocstrings.

Update triton version and image versions.

Added github publish workflow.

A small release for a fun little project with more to come.

For this initial release you can refer to the [README](https://github.com/aychang95/fastnn/blob/main/README.md) 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
- **Model Zoo**
- Various exported models hosted in this repo via. git-lfs and AWS S3. Includes models from the HuggingFace's Transformers and
TorchVision
- **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