Skip to content

Commit

Permalink
Merge pull request #15 from hotg-ai/embed-the-tutorial
Browse files Browse the repository at this point in the history
Embed the tutorial
  • Loading branch information
Michael Bryan authored Nov 6, 2021
2 parents 2ba908f + 87f5687 commit 0dcc4f7
Show file tree
Hide file tree
Showing 8 changed files with 120 additions and 633 deletions.
72 changes: 0 additions & 72 deletions docs/get_rune.mdx

This file was deleted.

72 changes: 1 addition & 71 deletions docs/get_started.mdx → docs/getting_started.mdx
Original file line number Diff line number Diff line change
@@ -1,82 +1,12 @@
---
title: Building a Rune - Quick Tutorial
sidebar_label: Getting Started
slug: /
slug: /getting-started
---

In this tutorial we will go from 0-60 on how to build a Rune, run it, serve it,
and test it on a mobile app.

## Setup and installation

There are a variety of installation methods you may use depending on your
development environment.

To use Rune you need:

- The `rune` CLI tool (see below)
- [The Rust compiler and toolchain][rustup] for compiling Runes to WebAssembly
- The `tinyverseml/rune-serve` Docker image for making your Rune accessible
without needing to upload to a registry

### GitHub Releases

Pre-compiled bundles containing the `rune` CLI tool and examples are available
on [our GitHub Releases page][latest-release] as the `rune.$target.zip` asset,
where `$target` is the [target triple][target-triple] corresponding to your OS
(e.g. `x86_64-apple-darwin` for x86 MacOS).

For those who like to live on the bleeding edge, [our nightly release][nightly]
contains the same assets but automatically generated from `master` every 24
hours.

### Install from Source

The `rune` CLI tool can be installed just like a normal Rust tool.

As well as requiring [the Rust toolchain](https://rustup.rs/), the Rune project
uses several native dependencies so you will need to install the following
before building:

- [`bindgen`](https://github.com/rust-lang/rust-bindgen) (`cargo install bindgen`)
- [Clang and LLVM](https://releases.llvm.org/download.html)
- [CMake](https://cmake.org/download/)
- [Docker](https://docs.docker.com/get-docker/) *(Linux only)*
- [Bazel](https://docs.bazel.build/versions/main/install.html) *(Windows and MacOS)*

You can then install the Rune CLI from crates.io:

```shell
$ cargo install hotg-rune-cli
```

Alternatively, if you want to live on the bleeding edge you can install it
directly from [the GitHub repository][rune-repo] (either `master` or a tagged
version):

```shell
$ cargo install --git https://github.com/hotg-ai/rune hotg-rune-cli

$ cargo install --git https://github.com/hotg-ai/rune hotg-rune-cli --rev v0.4.0
```

### Docker

Alternatively, you can use a docker image if you don't want to install the
`rune` CLI on your machine.

* We use docker for building, running, and serving runes. So make sure you have docker installed on your platform. We support the following platforms for building a rune:
- Mac (intel). M1/Arm chips are currently not supported.
- Windows 10
- Linux Ubuntu 16 and later
* Once you have docker installed you can pull the two docker containers hotg has built. Run these commands on your command line:

```shell
$ docker pull tinyverseml/rune-cli

$ docker pull tinyverseml/rune-serve
```

## Finding a Model

The first step of creating a Rune is to find (or train) a Machine Learning Model
Expand Down
6 changes: 3 additions & 3 deletions docs/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,6 @@ Tinyverse is an open platform for containerizing, shipping and running TinyML ap
Rune decouples your ML application from the underlying hardware. Using Rune you can
build, test and deploy your ML models faster to a variety of end devices.


## The Tinyverse platform

The Rune platform provides the ability for Machine Learning Engineers/Application package
Expand Down Expand Up @@ -111,11 +110,12 @@ the default registry configuration):
to the host for access to the `RAND` capability. The host can then provide floating points
and the input is process and prepared for the model.

## The underlying technology
## The Underlying Technology

Rune & Hammerd is written in the [Rust programming language](https://rust-lang.org/) and takes
advantage of several features of the [Webassembly](https://webassembly.org/) platform to deliver its functionality.

## Next steps
- Read about [installing Rune and Hammerd](/docs/get_rune).
- Read about [installing Rune and Hammerd](/docs/).
- Get hands-on experience with the tutorials [Getting started with Rune](/docs/tutorials/lesson-1/README)
tutorial.
65 changes: 0 additions & 65 deletions docs/proc_block_1.md

This file was deleted.

Loading

0 comments on commit 0dcc4f7

Please sign in to comment.