Skip to content

Update the readme file. #713

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

Update the readme file. #713

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a486a92
Update the Setting Up tutorial. (#728)
shoumikhin Oct 9, 2023
68e05ab
Update the readme file. (#713)
shoumikhin Oct 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 47 additions & 12 deletions docs/source/getting-started-setup.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,8 +55,23 @@ the required dependencies.

Follow these steps:

1. If you do not have it already, install conda on your machine by following
the steps in the [conda installation guide](https://conda.io/projects/conda/en/latest/user-guide/install/index.html).
1. If you do not have it already, install conda on your machine by following the
steps in the
[conda installation guide](https://conda.io/projects/conda/en/latest/user-guide/install/index.html).

1. Clone the `executorch` repository:

```bash
git clone [email protected]:pytorch/executorch.git
```

1. Update the submodules:

```bash
cd executorch
git submodule sync
git submodule update --init
```

1. Create and activate your conda environment:

Expand All @@ -65,26 +80,39 @@ the steps in the [conda installation guide](https://conda.io/projects/conda/en/l
conda activate executorch
```

1. Clone the `executorch` repository:
Or alternatively use a Python virtual environment:

```bash
git clone [email protected]:pytorch/executorch.git
python3 -m venv .executorch
source .executorch/bin/activate
```

1. Update the submodules:
1. Install [Cmake](https://cmake.org/download)

```bash
cd executorch
git submodule sync
git submodule update --init
conda install cmake
```

Alternatively:

```bash
pip install cmake
```

1. Install ExecuTorch and dependencies:

```bash
bash ./install_requirements.sh
./install_requirements.sh
```

1. Expose FlatBuffers compiler:

ExecuTorch uses `flatc` to export models and builds it from sources at
`third-party/flatbuffers`. Make it's available by referring in `$PATH`,
as prompted by the previous step, or exporting as `$FLATC_EXECUTABLE`
enironment variable.
Run `./build/install_flatc.sh` to make sure `flatc` is installed correctly.

You have successfully set up your environment to work with ExecuTorch. The next
step is to generate a sample ExecuTorch program.

Expand Down Expand Up @@ -178,18 +206,25 @@ Complete the following steps:
git submodule update --init
```

2. Configure Buck2 by decompressing with the following command (filename depends
1. Install ExecuTorch and dependencies:

```bash
./install_requirements.sh
```

1. Configure Buck2 by decompressing with the following command (filename depends
on your system):

```bash
# For example, buck2-x86_64-unknown-linux-musl.zst
# For example, buck2-x86_64-unknown-linux-musl.zst or buck2-aarch64-apple-darwin.zst
zstd -cdq buck2-DOWNLOADED_FILENAME.zst > /tmp/buck2 && chmod +x /tmp/buck2
```

You may want to copy the `buck2` binary into your `$PATH` so you can run it
as `buck2`.

3. Build a binary:
1. Build a binary:

```bash
/tmp/buck2 build //examples/portable/executor_runner:executor_runner --show-output
```
Expand Down
83 changes: 58 additions & 25 deletions docs/website/docs/tutorials/00_setting_up_executorch.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,60 +2,89 @@

# Setting up ExecuTorch

This is a tutorial for building and installing ExecuTorch from the GitHub repository.
This is a tutorial for building and installing ExecuTorch from the GitHub
repository.

## AOT Setup [(Open on Google Colab)](https://colab.research.google.com/drive/1m8iU4y7CRVelnnolK3ThS2l2gBo7QnAP#scrollTo=1o2t3LlYJQY5)
## Ahead-of-Time Setup [(Open on Google Colab)](https://colab.research.google.com/drive/1m8iU4y7CRVelnnolK3ThS2l2gBo7QnAP#scrollTo=1o2t3LlYJQY5)

This will install an `executorch` pip package to your conda environment and
allow you to export your PyTorch model to a flatbuffer file using ExecuTorch.

### Step 1: Set up a dev environment
### Step 1: Clone the ExecuTorch repo

To install conda, you can look at the
[conda installation guide](https://conda.io/projects/conda/en/latest/user-guide/install/index.html).
```bash
# Do one of these, depending on how your auth is set up
git clone https://github.com/pytorch/executorch.git
git clone [email protected]:pytorch/executorch.git
```

Ensure that git has fetched and updated the submodules. This is necessary
anytime commit hash of any of the submodules changes. Thus it is safe and
necessary at times to apply this step after you pull changes from upstream.

```bash
cd executorch
git submodule sync
git submodule update --init
```

### Step 2: Set up a dev environment

Install
[Conda](https://conda.io/projects/conda/en/latest/user-guide/install/index.html)
and activate a new virtual environment:

```bash
conda create -yn executorch python=3.10.0
conda activate executorch
```

conda install cmake
conda install -c conda-forge flatbuffers
Or alternatively, activate a new Python virtual environment:

```bash
python3 -m venv .executorch
source .executorch/bin/activate
```

### Step 2: Clone the `executorch` repo
### Step 3: Install [Cmake](https://cmake.org/download)

```bash
# Do one of these, depending on how your auth is set up
git clone https://github.com/pytorch/executorch.git
git clone [email protected]:pytorch/executorch.git
conda install cmake
```
Ensure that git has fetched and updated the submodules. This is necessary anytime
commit hash of any of the submodules changes. Thus it is safe and necessary at times to apply this step after you pull changes from upstream.

Alternatively:

```bash
cd executorch
git submodule sync
git submodule update --init
pip install cmake
```

### Step 3: Install `executorch` pip package and dependencies
### Step 4: Install `executorch` pip package and dependencies

Install all required python dependencies and PyTorch dependencies.

```bash
cd executorch
# Note: if you are behind a firewall an appropriate proxy server must be setup
# for all subsequent steps.
bash ./install_requirements.sh
./install_requirements.sh
```

When getting a new version of the executorch repo (via clone, fetch, or pull),
you may need to re-install a new version the PyTorch nightly pip package. The
`TORCH_VERSION` value in this document will be the correct version for the
corresponsing version of the repo.

### Step 4: Generate a program file from an `nn.Module`
### Step 5: Expose FlatBuffers compiler

ExecuTorch uses `flatc` to export models and builds it from sources at
`third-party/flatbuffers`. Make it's available by referring in `$PATH`,
as prompted by the previous step, or exporting as `$FLATC_EXECUTABLE`
enironment variable.
Run `./build/install_flatc.sh` to make sure `flatc` is installed correctly.

## Testing Model Export

Generate a test program file from an `nn.Module` via Python script:

Via python script:
```bash
# Creates the file `add.pte`
python3 -m examples.portable.scripts.export --model_name="add"
Expand All @@ -64,7 +93,8 @@ python3 -m examples.portable.scripts.export --model_name="add"
python3 -m examples.portable.scripts.export_and_delegate --option "composite"
```

Or via python interpreter:
Or via Python interpreter:

```python
$ python3
>>> import executorch.exir as exir
Expand All @@ -74,11 +104,14 @@ $ python3
>>> open("mul.pte", "wb").write(exir.capture(m, m.get_random_inputs()).to_edge().to_executorch().buffer)
```

Please refer to the [More Examples](./00_setting_up_executorch.md#more-examples) section for running with more popular models.
Please refer to the [More Examples](./00_setting_up_executorch.md#more-examples)
section for running with more popular models.

## Runtime Setup

Follow [AOT Setup: Step 2](./00_setting_up_executorch.md#step-2-clone-the-executorch-repo) above to clone the `executorch` repo if you haven't already.
Follow
[Ahead-of-Time Setup: Step 1](./00_setting_up_executorch.md#step-1-clone-the-executorch-repo)
above to clone the `executorch` repo if you haven't already.

### Step 1: Install buck2

Expand All @@ -87,7 +120,7 @@ Follow [AOT Setup: Step 2](./00_setting_up_executorch.md#step-2-clone-the-execut
- Decompress with the following command (filename depends on your system)

```bash
# For example, buck2-x86_64-unknown-linux-musl.zst
# For example, buck2-x86_64-unknown-linux-musl.zst or buck2-aarch64-apple-darwin.zst
zstd -cdq buck2-DOWNLOADED_FILENAME.zst > /tmp/buck2 && chmod +x /tmp/buck2
```

Expand Down
Loading