[Doc] update docker readme files to include Python versions (ray-proj…

…ect#25099) Similar to ray-project#25053, update the documentations on the docker site.
pabloem · May 26, 2022 · b2d41fc · b2d41fc
1 parent dd3a43b
commit b2d41fc
Show file tree

Hide file tree

Showing 5 changed files with 84 additions and 50 deletions.
diff --git a/docker/autoscaler/README.md b/docker/autoscaler/README.md
@@ -1,11 +1 @@
 # DEPRECATED -- Please use [`rayproject/ray-ml`](https://hub.docker.com/repository/docker/rayproject/ray-ml)
-## About
-This image used to be the base image for the Ray autoscaler, but it has been replaced by [`rayproject/ray-ml`](https://hub.docker.com/repository/docker/rayproject/ray-ml). 
-Please use that instead, *this image is deprecated*.
-
-
-## Tags
-* [`:latest`](https://hub.docker.com/repository/docker/rayproject/autoscaler/tags?page=1&name=latest) - The most recent Ray release.
-* `:1.x.x` - A specific release build. 
-* [`:nightly`](https://hub.docker.com/repository/docker/rayproject/autoscaler/tags?page=1&name=nightly) - The most recent nightly build.
-* `:SHA` - A specific nightly build.
diff --git a/docker/base-deps/README.md b/docker/base-deps/README.md
@@ -4,19 +4,27 @@ This is an internal image, the [`rayproject/ray`](https://hub.docker.com/reposit
 
 This image  has the system-level dependencies for `Ray` and the `Ray Autoscaler`. The `ray-deps` image is built on top of this. This image is built periodically or when dependencies are added. [Find the Dockerfile here.](https://github.com/ray-project/ray/blob/master/docker/base-deps/Dockerfile)
 
+## Tags
 
+Images are `tagged` with the format `{Ray version}[-{Python version}][-{Platform}]`. `Ray version` tag can be one of the following:
 
+| Ray version tag | Description |
+| --------------- | ----------- |
+| `latest`                     | The most recent Ray release. |
+| `x.y.z`                      | A specific Ray release, e.g. 1.12.1 |
+| `nightly`                    | The most recent Ray development build (a recent commit from Github `master`) |
+| `6 character Git SHA prefix` | A specific development build (uses a SHA from the Github `master`, e.g. `8960af`). |
 
-## Tags
-* [`:latest`](https://hub.docker.com/repository/docker/rayproject/base-deps/tags?page=1&name=latest) - The most recent Ray release.
-* `:1.x.x` - A specific release build. 
-* [`:nightly`](https://hub.docker.com/repository/docker/rayproject/base-deps/tags?page=1&name=nightly) - The most recent nightly build.
-* `:DATE` - A specific build.
-
-### Suffixes
-* `-cuXXX` - These are based off of an `NVIDIA CUDA` image. They require the [Nvidia Docker Runtime](https://github.com/NVIDIA/nvidia-docker) to be installed on the host for the container to access GPUs.  
-* `-cpu`- These are based off of an `Ubuntu` image.
-* Tags without a suffix refer to `-cpu` images
+The optional `Python version` tag specifies the Python version in the image. All Python versions supported by Ray are available, e.g. `py37`, `py38`, `py39` and `py310`. If unspecified, the tag points to an image using `Python 3.7`.
+
+The optional `Platform` tag specifies the platform where the image is intended for:
+
+| Platform tag | Description |
+| --------------- | ----------- |
+| `-cpu`  | These are based off of an Ubuntu image. |
+| `-cuXX` | These are based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the Nvidia Docker Runtime. |
+| `-gpu`  | Aliases to a specific `-cuXX` tagged image. |
+| no tag  | Aliases to `-cpu` tagged images for `ray`, and aliases to ``-gpu`` tagged images for `ray-ml`. |
 
 ## Other Images
 * [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) - Ray and all of its dependencies.

diff --git a/docker/ray-deps/README.md b/docker/ray-deps/README.md
@@ -3,19 +3,27 @@ This is an internal image, the [`rayproject/ray`](https://hub.docker.com/reposit
 
 This has the python-level dependencies for `Ray` and the `Ray Autoscaler`. The `ray` image is built on top of this. This image is built periodically or when dependencies are added. [Find the Dockerfile here.](https://github.com/ray-project/ray/blob/master/docker/ray-deps/Dockerfile)
 
+## Tags
 
+Images are `tagged` with the format `{Ray version}[-{Python version}][-{Platform}]`. `Ray version` tag can be one of the following:
 
+| Ray version tag | Description |
+| --------------- | ----------- |
+| `latest`                     | The most recent Ray release. |
+| `x.y.z`                      | A specific Ray release, e.g. 1.12.1 |
+| `nightly`                    | The most recent Ray development build (a recent commit from Github `master`) |
+| `6 character Git SHA prefix` | A specific development build (uses a SHA from the Github `master`, e.g. `8960af`). |
 
-## Tags
-* [`:latest`](https://hub.docker.com/repository/docker/rayproject/ray-deps/tags?page=1&name=latest) - The most recent Ray release.
-* `:1.x.x` - A specific release build. 
-* [`:nightly`](https://hub.docker.com/repository/docker/rayproject/ray-deps/tags?page=1&name=nightly) - The most recent nightly build.
-* `:DATE` - A specific build.
-
-### Suffixes
-* `-cuXXX` - These are based off of an `NVIDIA CUDA` image. They require the [Nvidia Docker Runtime](https://github.com/NVIDIA/nvidia-docker) to be installed on the host for the container to access GPUs.  
-* `-cpu`- These are based off of an `Ubuntu` image.
-* Tags without a suffix refer to `-cpu` images
+The optional `Python version` tag specifies the Python version in the image. All Python versions supported by Ray are available, e.g. `py37`, `py38`, `py39` and `py310`. If unspecified, the tag points to an image using `Python 3.7`.
+
+The optional `Platform` tag specifies the platform where the image is intended for:
+
+| Platform tag | Description |
+| --------------- | ----------- |
+| `-cpu`  | These are based off of an Ubuntu image. |
+| `-cuXX` | These are based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the Nvidia Docker Runtime. |
+| `-gpu`  | Aliases to a specific `-cuXX` tagged image. |
+| no tag  | Aliases to `-cpu` tagged images for `ray`, and aliases to ``-gpu`` tagged images for `ray-ml`. |
 
 ## Other Images
 * [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) - Ray and all of its dependencies.

diff --git a/docker/ray-ml/README.md b/docker/ray-ml/README.md
@@ -1,19 +1,33 @@
 ## About
 This image is an extension of the [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) image. It includes all extended requirements of `RLlib`, `Serve` and `Tune`. It is a well-provisioned starting point for trying out the Ray ecosystem. [Find the Dockerfile here.](https://github.com/ray-project/ray/blob/master/docker/ray-ml/Dockerfile)
 
+## Tags
 
+Images are `tagged` with the format `{Ray version}[-{Python version}][-{Platform}]`. `Ray version` tag can be one of the following:
 
+| Ray version tag | Description |
+| --------------- | ----------- |
+| `latest`                     | The most recent Ray release. |
+| `x.y.z`                      | A specific Ray release, e.g. 1.12.1 |
+| `nightly`                    | The most recent Ray development build (a recent commit from Github `master`) |
+| `6 character Git SHA prefix` | A specific development build (uses a SHA from the Github `master`, e.g. `8960af`). |
 
-## Tags
-* [`:latest`](https://hub.docker.com/repository/docker/rayproject/ray-ml/tags?page=1&name=latest) - The most recent Ray release.
-* `:1.x.x` - A specific release build. 
-* [`:nightly`](https://hub.docker.com/repository/docker/rayproject/ray-ml/tags?page=1&name=nightly) - The most recent nightly build.
-* `:SHA` - A specific nightly build.
-
-### Suffixes
-* `-cpu` - These are based off of a Ubuntu image.
-* `-gpu` - These are based off of an `NVIDIA CUDA` image. They require the [Nvidia Docker Runtime](https://github.com/NVIDIA/nvidia-docker) to be installed on the host for the container to access GPUs.
-* Tags without a suffix refer to `-gpu` image
+The optional `Python version` tag specifies the Python version in the image. All Python versions supported by Ray are available, e.g. `py37`, `py38`, `py39` and `py310`. If unspecified, the tag points to an image using `Python 3.7`.
+
+The optional `Platform` tag specifies the platform where the image is intended for:
+
+| Platform tag | Description |
+| --------------- | ----------- |
+| `-cpu`  | These are based off of an Ubuntu image. |
+| `-cuXX` | These are based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the Nvidia Docker Runtime. |
+| `-gpu`  | Aliases to a specific `-cuXX` tagged image. |
+| no tag  | Aliases to `-cpu` tagged images for `ray`, and aliases to ``-gpu`` tagged images for `ray-ml`. |
+
+Examples tags:
+- none: equivalent to `latest`
+- `latest`: equivalent to `latest-py37-gpu`, i.e. image for the most recent Ray release
+- `nightly-py38-cpu`
+- `806c18-py38-cu112`
 
 ## Other Images
 * [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) - Ray and all of its dependencies.
diff --git a/docker/ray/README.md b/docker/ray/README.md
@@ -2,19 +2,33 @@
 Default docker images for [Ray](https://github.com/ray-project/ray)! This includes
 everything needed to get started with running Ray! They work for both local development and *are ideal* for use with the [Ray Cluster Launcher](https://docs.ray.io/en/master/cluster/cloud.html). [Find the Dockerfile here.](https://github.com/ray-project/ray/blob/master/docker/ray/Dockerfile)
 
+## Tags
 
+Images are `tagged` with the format `{Ray version}[-{Python version}][-{Platform}]`. `Ray version` tag can be one of the following:
 
+| Ray version tag | Description |
+| --------------- | ----------- |
+| `latest`                     | The most recent Ray release. |
+| `x.y.z`                      | A specific Ray release, e.g. 1.12.1 |
+| `nightly`                    | The most recent Ray development build (a recent commit from Github `master`) |
+| `6 character Git SHA prefix` | A specific development build (uses a SHA from the Github `master`, e.g. `8960af`). |
 
-## Tags
-* [`:latest`](https://hub.docker.com/repository/docker/rayproject/ray/tags?page=1&name=latest) - The most recent Ray release.
-* `:1.x.x` - A specific release build. 
-* [`:nightly`](https://hub.docker.com/repository/docker/rayproject/ray/tags?page=1&name=nightly) - The most recent nightly build.
-* `:SHA` - A specific nightly build.
-
-### Suffixes
-* `-cuXXX` - These are based off of an `NVIDIA CUDA` image. They require the [Nvidia Docker Runtime](https://github.com/NVIDIA/nvidia-docker) to be installed on the host for the container to access GPUs.  
-* `-cpu`- These are based off of an `Ubuntu` image.
-* Tags without a suffix refer to `-cpu` images
+The optional `Python version` tag specifies the Python version in the image. All Python versions supported by Ray are available, e.g. `py37`, `py38`, `py39` and `py310`. If unspecified, the tag points to an image using `Python 3.7`.
+
+The optional `Platform` tag specifies the platform where the image is intended for:
+
+| Platform tag | Description |
+| --------------- | ----------- |
+| `-cpu`  | These are based off of an Ubuntu image. |
+| `-cuXX` | These are based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the Nvidia Docker Runtime. |
+| `-gpu`  | Aliases to a specific `-cuXX` tagged image. |
+| no tag  | Aliases to `-cpu` tagged images for `ray`, and aliases to ``-gpu`` tagged images for `ray-ml`. |
+
+Examples tags:
+- none: equivalent to `latest`
+- `latest`: equivalent to `latest-py37-cpu`, i.e. image for the most recent Ray release
+- `nightly-py38-cpu`
+- `806c18-py38-cu112`
 
 ## Other Images
 * [`rayproject/ray-ml`](https://hub.docker.com/repository/docker/rayproject/ray-ml) - This image with common ML libraries to make development & deployment more smooth!