Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
experimental-experiment 0.1.0 documentation
Logo
experimental-experiment 0.1.0 documentation

Contents

  • Tutorial
    • pytorch and onnx
      • 101: Linear Regression and export to ONNX
      • 101: A custom backend for torch
      • 101: Graph Optimization
      • 102: Convolution and Matrix Multiplication
      • 102: Fuse kernels in a small Llama Model
      • 102: Measure LLAMA speed
      • 201: Evaluate different ways to export a torch model to ONNX
      • 201: Evaluate DORT
      • 201: Evaluate DORT Training
      • 301: Compares LLAMA exporters
      • 301: Compares LLAMA exporters for onnxrt backend
    • onnx
      • 101: Profile an existing model with onnxruntime
    • Frequent Exceptions
    • Start from a docker
  • Design
    • Custom Exporter
    • Pattern Optimizer
    • Dynamo Backends
  • API
    • onnx_export
    • graph_builder
    • graph_builder_optim
    • Optimization Patterns
    • order_optim
    • interpreter
    • aten_functions
    • aten_methods
    • aten_prims
    • torch_dynamo
    • Dimension
    • experimental_experiment.args
    • experimental_experiment.bench_run
    • experimental_experiment.model_run
    • gradient
    • reference
    • TorchModelContainer
    • torch_models
    • Testing
    • convert_tools
    • Others…
  • Example gallery
    • 101: Graph Optimization
    • 101: Profile an existing model with onnxruntime
    • 101: Onnx Model Rewriting
    • 101: Linear Regression and export to ONNX
    • 101: A custom backend for torch
    • 102: Convolution and Matrix Multiplication
    • 102: Fuse kernels in a small Llama Model
    • 301: Compares LLAMA exporters
    • 301: Compares LLAMA exporters for onnxrt backend
    • 102: Measure LLAMA speed
    • 201: Evaluate DORT Training
    • 201: Evaluate DORT
    • 201: Evaluate different ways to export a torch model to ONNX
  • Supported Models
    • Tries with Undocumented
    • Use the custom exporter in torch
    • A script to report a bug
    • CodeLlama
    • LLaMa
    • Mistral
    • Phi
    • Phi3
    • Speech2Text2ForCausalLM
  • Command Lines
    • Benchmarks from the command line
      • experimental_experiment.torch_bench.dort_bench
      • experimental_experiment.torch_bench.dort_profile
      • Measuring the exporters on a short list of sets of models
      • Interesting scripts or command lines
    • Tools from the command line
      • python -m experimental_experiment lighten and unlighten
      • python -m experimental_experiment optimize
      • python -m experimental_experiment run
  • Times

More

  • Change Logs
  • License
  • Long Outputs uneasy to read
Back to top
View this page

experimental-experiment: fuzzy work¶

https://dev.azure.com/xavierdupre3/experimental-experiment/_apis/build/status/sdpython.experimental-experiment https://badge.fury.io/py/experimental-experiment.svg GitHub Issues MIT License size https://img.shields.io/badge/code%20style-black-000000.svg https://codecov.io/gh/sdpython/experimental-experiment/branch/main/graph/badge.svg?token=Wb9ZGDta8J

experimental-experiment is mostly to experiment ideas.

Source are sdpython/experimental-experiment.

Contents

  • Tutorial
  • Design
  • API
  • Example gallery
  • Supported Models
  • Command Lines
  • Times

More

  • Change Logs
  • License
  • Long Outputs uneasy to read

Older versions¶

  • 0.1.0

The documentation was updated on:

    2024-10-01 13:36:09.538738
Next
Tutorial
Copyright © 2023-2024
Made with Sphinx and @pradyunsg's Furo
On this page
  • experimental-experiment: fuzzy work
    • Older versions