Adds a page describing a development workflow for Serve applications.
Co-authored-by: Edward Oakes <ed.nmi.oakes@gmail.com>
Co-authored-by: shrekris-anyscale <92341594+shrekris-anyscale@users.noreply.github.com>
Co-authored-by: Stephanie Wang <swang@cs.berkeley.edu>
The "Monitoring Ray Serve" page explains how to inspect your Ray Serve applications. This change updates the page to remove outdated metrics that Serve no longer exposes and to upgrade code samples to use 2.0 APIs. It also improves the content's readability and organization.
Link to updated "Monitoring Ray Serve" page: https://ray--27777.org.readthedocs.build/en/27777/serve/monitoring.html
A new feature was recently added, where Serve replicas are not restarted if only `num_replicas`, `autoscaling_config`, and/or `user_config` is updated in the config file that's redeployed. Updating docs to talk about this feature.
Co-authored-by: shrekris-anyscale <92341594+shrekris-anyscale@users.noreply.github.com>
This PR is an edit pass on the Performance Tuning page after reading it with fresh eyes. None of the content was out of date so it's mostly nits and rewording some parts that were slightly confusing.
Integration between Ray Serve and Gradio. Users of Gradio can wrap their Gradio app in a Serve deployment by using `GradioIngress`, and scale it up through more replicas or more CPU/GPU resources.
- Move autoscaling architecture from autoscaling page to architecture page
- Update architecture page
- Remove "Router" actor
- Update description of ServeHandle
- Update defaults about HTTPproxy (default one on each node -> default just one per cluster, on the head node)
- Add note about fault tolerance in different failure scenarios
- Assorted typos/usage nits
Co-authored-by: shrekris-anyscale <92341594+shrekris-anyscale@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
Removes deprecated APIs:
- serve.start()
- get_handle()
Rewrites the ServeHandle doc snippet to use the recommended workflow for ServeHandles (only access them from other deployments, pass Deployments in as input args to `.bind()`, which get resolved to ServeHandles at runtime)
Co-authored-by: shrekris-anyscale <92341594+shrekris-anyscale@users.noreply.github.com>
The Serve CLI and REST API always sets the host to `0.0.0.0` and the port to Serve's default. This change adds `host` and `port` as top level options in the Serve config file, so users can manually set the host and port of their Serve application to different values.
This change introduces a new Serve config file format:
```yaml
import_path: ...
runtime_env: ...
host: ...
port: ...
deployments: ...
...
```
`host` and `port` are optional and can be omitted. A running Serve application's `host` and `port` cannot be changed. If a user tries to `serve deploy` a config file with different `host` and `port` options than an already-running Serve application, `serve deploy` will fail without making any changes to the application. The user must `serve shutdown` their application and restart it with `serve deploy` to change their `host` and `port`.
**Follow-Up Items**
* The following CLI commands should **not** start Serve automatically. They should check whether Serve is running and perform some sort of no-op if it's not. That would alleviate the concern that the user starts Serve by accident through a `GET` request and needs to deal with default `host`/`port` options. Corresponding docs should also be updated.
* `serve status`
* `serve config`
* `serve shutdown`
ray.init() will currently start a new Ray instance even if one is already existing, which is very confusing if you are a new user trying to go from local development to a cluster. This PR changes it so that, when no address is specified, we first try to find an existing Ray cluster that was created through `ray start`. If none is found, we will start a new one.
This makes two changes to the ray.init() resolution order:
1. When `ray start` is called, the started cluster address was already written to a file called `/tmp/ray/ray_current_cluster`. For ray.init() and ray.init(address="auto"), we will first check this local file for an existing cluster address. The file is deleted on `ray stop`. If the file is empty, autodetect any running cluster (legacy behavior) if address="auto", or we will start a new local Ray instance if address=None.
2. When ray.init(address="local") is called, we will create a new local Ray instance, even if one is already existing. This behavior seems to be necessary mainly for `ray.client` use cases.
This also surfaces the logs about which Ray instance we are connecting to. Previously these were hidden because we didn't set up the log until after connecting to Ray. So now Ray will log one of the following messages during ray.init:
```
(Connecting to existing Ray cluster at address: <IP>...)
...connection...
(Started a local Ray cluster.| Connected to Ray Cluster.)( View the dashboard at <URL>)
```
Note that this changes the dashboard URL to be printed with `ray.init()` instead of when the dashboard is first started.
Co-authored-by: Eric Liang <ekhliang@gmail.com>
In Ray 2.0, we want to achieve api server HA.
Originally serve endpoints are in head node.
This pr moves serve endpoints to dashboard agents, so they will be HA due to multiple replica of dashboard agent.
- new section of doc for autoscaling (introduction of serve autoscaling and config parameter)
- Remove the version requirement note inside the doc
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Edward Oakes <ed.nmi.oakes@gmail.com>
Co-authored-by: shrekris-anyscale <92341594+shrekris-anyscale@users.noreply.github.com>
Co-authored-by: Archit Kulkarni <architkulkarni@users.noreply.github.com>
Enable checking of the ray core module, excluding serve, workflows, and tune, in ./ci/lint/check_api_annotations.py. This required moving many files to ray._private and associated fixes.
