|
|
site_name: transformer-deploy by Lefebvre Dalloz |
|
|
repo_name: ELS-RD/transformer-deploy/ |
|
|
repo_url: https://github.com/ELS-RD/transformer-deploy/ |
|
|
site_description: Efficient, scalable and enterprise-grade CPU/GPU inference server for Hugging Face transformer models |
|
|
copyright: Copyright © 2020 - 2021 Lefebvre Dalloz |
|
|
edit_uri: "" |
|
|
|
|
|
theme: |
|
|
name: material |
|
|
custom_dir: docs/overrides |
|
|
palette: |
|
|
scheme: default |
|
|
primary: black |
|
|
accent: deep orange |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
icon: |
|
|
repo: fontawesome/brands/github |
|
|
logo: material/speedometer |
|
|
|
|
|
markdown_extensions: |
|
|
- admonition |
|
|
- pymdownx.details |
|
|
- pymdownx.superfences |
|
|
- pymdownx.emoji: |
|
|
emoji_index: !!python/name:materialx.emoji.twemoji |
|
|
emoji_generator: !!python/name:materialx.emoji.to_svg |
|
|
- pymdownx.highlight: |
|
|
anchor_linenums: true |
|
|
- pymdownx.inlinehilite |
|
|
- pymdownx.snippets |
|
|
- pymdownx.superfences |
|
|
- toc: |
|
|
permalink: "#" |
|
|
- pymdownx.critic |
|
|
- pymdownx.caret |
|
|
- pymdownx.mark |
|
|
- pymdownx.tilde |
|
|
- abbr |
|
|
- attr_list |
|
|
- md_in_html |
|
|
|
|
|
plugins: |
|
|
- search |
|
|
- mkdocstrings: |
|
|
handlers: |
|
|
python: |
|
|
selection: |
|
|
docstring_style: restructured-text |
|
|
- include-markdown |
|
|
- mkdocs-jupyter: |
|
|
theme: dark |
|
|
ignore_h1_titles: True |
|
|
- gen-files: |
|
|
scripts: |
|
|
- resources/gen_doc_stubs.py |
|
|
- literate-nav: |
|
|
nav_file: SUMMARY.md |
|
|
|
|
|
extra: |
|
|
social: |
|
|
- icon: fontawesome/brands/twitter |
|
|
link: https://twitter.com/pommedeterre33 |
|
|
- icon: fontawesome/brands/medium |
|
|
link: https://medium.com/@pommedeterre33 |
|
|
generator: false |
|
|
|
|
|
nav: |
|
|
- Getting started: index.md |
|
|
- Installation (local or Docker only): setup_local.md |
|
|
- Run (1 command): run.md |
|
|
- Which tool to choose for your inference?: compare.md |
|
|
- How ONNX conversion works? : onnx_convert.md |
|
|
- Understanding model optimization : optimizations.md |
|
|
- Direct use TensorRT in Python script (no server): python.md |
|
|
- GPU quantization for X2 speed-up: |
|
|
- Why using quantization?: quantization/quantization_intro.md |
|
|
- Quantization theory: quantization/quantization_theory.md |
|
|
- How is it implemented in this library?: quantization/quantization_ast.md |
|
|
- PTQ and QAT, what are they?: quantization/quantization_ptq.md |
|
|
- End to end demo: quantization/quantization.ipynb |
|
|
- "From optimization to deployment: end to end demo": demo.md |
|
|
- "Accelerate text generation with GPT-2": gpt2.ipynb |
|
|
- "Accelerate text generation with T5": t5.ipynb |
|
|
- Benchmarks run on AWS GPU instances: benchmarks.md |
|
|
- FAQ: faq.md |
|
|
- API: reference/ |
|
|
|
