Commit Graph
35 Commits
Author SHA1 Message Date
Ian RodneyandGitHub 1d158dda32 [serve] Rename to use replicas, not workers (#11822) 2020-11-10 11:36:15 -08:00
Edward OakesandGitHub 1c132f2ff8 [serve] Improve DEBUG logging for understanding perf (#11838) 2020-11-09 14:10:42 -06:00
SangBin ChoandGitHub 109481afd9 [Metric] custom metrics refinement (#10861)
* In progress

* In Progress.

* Addressed code review.

* Add unit tests.

* Add a simple doc.

* Fixed test failure.

* Fix all test failures from serve.

* Addressed code review.
2020-09-25 09:10:28 -07:00
Simon MoandGitHub 55b6c19d98 [Serve] Implement ServeHandle refactoring (#10527) 2020-09-04 15:50:56 -07:00
Edward OakesandGitHub 786f12edfd [serve] Serve client refactor (#10409) 2020-09-04 12:02:23 -05:00
Simon MoandGitHub 94374e1dd9 [Serve] Add Latency and Queue Size Metrics (#10535) 2020-09-03 17:33:37 -07:00
Simon MoandGitHub 65f17f2e14 [Serve] Refactor RequestMetadata and Query objects (#10483) 2020-09-01 18:15:31 -07:00
Simon MoandGitHub ed3fdd2c0b [Serve] Remove register_custom_serializer (#10331) 2020-08-25 21:20:43 -07:00
Edward OakesandGitHub 888f0a2c60 [serve] Use ray.experimental.metrics (#10185) 2020-08-19 13:03:22 -05:00
Edward OakesandGitHub ba0f531da0 [serve] Remove SLO code and blist dependency (#10075) 2020-08-18 17:52:36 -05:00
Edward OakesandGitHub 38408574c4 [serve] Basic autoscaling policy (#9845) 2020-08-05 21:11:35 -05:00
Simon MoandGitHub a078a21437 [Serve] Allow multiple HTTP servers. (#9523) 2020-07-24 12:41:20 -07:00
Ian RodneyandGitHub b8fc259796 [serve] Rename to Controller (#9566) 2020-07-20 12:50:29 -07:00
Simon MoandGitHub d0398bf7e1 [Serve] Serialize Query object directly (#9490) 2020-07-20 10:10:07 -07:00
Simon MoandGitHub 60a838f0f0 [Serve] Use pickle instead of clouldpickle (#9479) 2020-07-16 15:44:10 -07:00
Simon MoandGitHub d4a5d09dab [Serve] Merge router with HTTPProxy (#9225) 2020-07-10 13:52:48 -07:00
Hao ChenandGitHub d49dadf891 Change Python's ObjectID to ObjectRef (#9353) 2020-07-10 17:49:04 +08:00
Edward OakesandGitHub aa3fd62cac [serve] Add shadow traffic API (#9106) 2020-06-25 10:55:22 -05:00
Simon MoandGitHub 6c3062906f [Serve] Batching in Worker Replica (#8709) 2020-06-09 11:29:16 -07:00
Edward OakesandGitHub 4155d5830f [serve] Replace actor error retry logic with max_task_retries (#8768) 2020-06-05 10:45:28 -05:00
Edward OakesandGitHub 0306e4d589 [serve] Refer to serve "instances," not "clusters" (#8746) 2020-06-02 15:16:29 -07:00
Simon MoandGitHub 4cef1ee591 [Serve] Cleanup Router Implementation (#8718) 2020-06-01 19:21:28 -07:00
Edward OakesandGitHub 85cb721f19 [serve] Fix worker replica leak (#8506) 2020-05-19 20:51:50 -05:00
Edward OakesandGitHub fb23bd6fc0 [serve] Optionally namespace serve clusters (#8447) 2020-05-17 00:14:42 -05:00
Edward OakesandGitHub ef498e8aa5 [serve] Add basic session affinity via shard key (#8449) 2020-05-15 16:18:52 -05:00
Edward OakesandGitHub bb494a3be8 [serve] Refactor router policies to remove inheritance (#8372) 2020-05-12 12:34:01 -05:00
Simon MoandGitHub c5a5a5de89 [Serve] Refactor Metric System: Counter + Measure Support (#8114) 2020-05-06 17:44:02 -07:00
Edward OakesandGitHub 63bc7dc522 service -> endpoint in router (#8269) 2020-05-01 11:55:34 -05:00
Edward OakesandGitHub 6373c70661 [serve] Refactor BackendConfig (#8202) 2020-04-30 22:31:07 -05:00
Edward OakesandGitHub 95d187e556 [serve] Add delete_endpoint call (#8256) 2020-04-30 20:59:07 -05:00
Edward OakesandGitHub 43be73e4cf [serve] Add delete_backend call (#8252) 2020-04-30 13:10:39 -05:00
Edward OakesandGitHub 7c0200c93b [serve] Master actor fault tolerance (#8116) 2020-04-28 15:52:29 -05:00
Edward OakesandGitHub da296bf8c5 [serve] Router fault tolerance (#8008) 2020-04-19 11:04:06 -05:00
Edward OakesandGitHub 2cb9cfb2b6 [serve] Make workers fault tolerant (#7970) 2020-04-12 11:48:08 -05:00
Edward OakesandGitHub 7be7af11ab [serve] Push requests to workers instead of polling via dequeue_request (#7965) 2020-04-10 14:47:03 -05:00