shrekris-anyscale

[Serve] Trim Ray Serve's "Getting Started" Page

1

## Why are these changes needed? Ray Serve's "Getting Started" page has a lot of content. This change removes the following sections: * Scaling out * Fine-grained resource allocation *...

Signed-off-by: Shreyas Krishnaswamy ## Why are these changes needed? Ray Serve's documentation lists some general benchmarks. This change adds benchmarks based on the nightly Serve release tests. ## Related issue...

### Description Ray Serve surfaces system metrics for debugging. [The metrics documentation](https://docs.ray.io/en/releases-1.13.0/serve/monitoring.html#metrics) is outdated and contains metrics that no longer exist. For example, the metrics `serve_backend_queuing_latency_ms` and `serve_replica_queued_queries` seem to...

Signed-off-by: Shreyas Krishnaswamy ## Why are these changes needed? **Background** Serve sets deployment config defaults directly via keyword arguments in the `@serve.deployment` decorator. This makes it it makes it impossible...

### What happened + What you expected to happen From [a Ray Slack thread](https://ray-distributed.slack.com/archives/C02GFQ82JPM/p1663343998548389): > [A user is] working with Kuberay and Ray 2.0.0 and try to deploy a RayService....

[Bug] `RayService` restarts repeatedly when a new config is applied

1

### Search before asking - [X] I searched the [issues](https://github.com/ray-project/kuberay/issues) and found no similar issues. ### KubeRay Component Others ### What happened + What you expected to happen A user...

[RayService] [GCS FT] Worker nodes don't serve traffic while head node is down

3

### Search before asking - [X] I searched the [issues](https://github.com/ray-project/kuberay/issues) and found no similar issues. ### KubeRay Component Others ### What happened + What you expected to happen I had...

Signed-off-by: Shreyas Krishnaswamy ## Why are these changes needed? When users submit a malformed Serve config (e.g. with invalid fields) via `PUT` request, they receive a 500 error. This change...

## Background and Expected Behavior `ExponentialRetry` takes in [the following arguments](https://github.com/inyutin/aiohttp_retry/blob/ba2169891f5b32a5c59e48ca185dd8e68e44ded7/aiohttp_retry/retry_options.py#L38-L49): ```python class ExponentialRetry(RetryOptionsBase): def __init__( self, attempts: int = 3, # How many times we should retry start_timeout: float...