Add GPT-2 acceleration support

• add support for decoder based model (GPT-2) on both ONNX Runtime and TensorRT
• refactor triton configuration generation (simplification)
• add GPT-2 model documentation (notebook)
• fix CPU quantization benchmark (was not using the quant model)
• fix sentence transformers bug

add CPU support and generic GPU quantization support

What's Changed

• Update requirements_gpu.txt by @sam-writer in #22
• refactoring by @pommedeterresautee in #27
• add CPU inference support by @pommedeterresautee in #28
• Add QAT support to more models by @pommedeterresautee in #29

Full Changelog: v0.2.0...v0.3.0

add GPU quantization support

• support int-8 GPU quantization
• add a tuto to perform quantization end to end
• add QDQRoberta model
• switch to ONNX opset 13
• refactoring in the TensorRT engine creation
• fix bugs
• add auth token (for private HF repo)

What's Changed

• Update triton by @pommedeterresautee in #11
• fix README.md by @pommedeterresautee in #13
• Fix install errors by @sam-writer in #20
• Add auth token by @sam-writer in #19
• Support GPU INT-8 quantization by @pommedeterresautee in #15

New Contributors

• @sam-writer made their first contribution in #20

Full Changelog: v0.1.1...v0.2.0

update Triton image to 21.11-py3

• update Docker image
• update documentation

from PoC to library

• switch from a proof of concept to a library
• add support for TensorRT Python API (for best performances)
• improve documentation (separate Hugging Face Infinity thing from the doc, add benchmark, etc.)
• fix issues with mixed precision
• add license
• add tests, Github actions, Makefile
• change the way the Docker image is built

first release

all the scripts to reproduce https://medium.com/p/e1be0057a51c