Eric Liang
95b5ad12ba
Initial version of workflow documentation ( #18138 )
2021-08-27 16:20:48 -07:00
Jiao
c7e38ceb10
[serve] Better constructor failure handling ( #16922 )
2021-08-27 18:05:22 -05:00
mwtian
26679d62c5
[Core][ObjectRef] Change default to not record call stack during ObjectRef creation ( #18078 )
2021-08-27 15:45:34 -07:00
Clark Zinzow
c0598de82a
[Datasets] Port write APIs to use file-based datasources. ( #18135 )
2021-08-27 15:24:54 -07:00
Chen Shen
28e6ae5ce0
[Test] fix object spilling 2 ( #18141 )
2021-08-27 13:52:42 -07:00
Clark Zinzow
aee7ba2510
[Datasets] Add from_numpy() and to_numpy() APIs ( #18146 )
2021-08-27 13:33:11 -07:00
Yi Cheng
ed7124663a
[workflow] Fix nested workflow with catch exception bug ( #18145 )
2021-08-27 10:53:15 -07:00
Chen Shen
feeb20e920
[CI][rfc] Fix flaky test_multi_node:test_cleanup_on_driver_exit
2021-08-27 10:51:01 -07:00
Joseph Suarez
8136d2912b
[RLlib] Add policies arg to callback: on_episode_step (already exists in all other episode-related callbacks) ( #18119 )
2021-08-27 16:12:19 +02:00
Tao Wang
7620afb8be
[Deploy]Don't start shard redis in local if we specify external redis. ( #17856 )
...
* Don't start shard redis in local if we specify external redis
* lint
* reuse primary as shard
* add test
* lint
* lint
* lint
2021-08-27 16:45:09 +08:00
SangBin Cho
a25cc47399
[Core] Set keepalive only at gcs ( #18086 )
2021-08-27 01:26:51 -07:00
Antoni Baum
56089ae926
[tune] Add max_concurrent_trials argument to tune.run ( #17905 )
...
Co-authored-by: Kai Fricke <krfricke@users.noreply.github.com>
2021-08-27 09:12:50 +02:00
xwjiang2010
cc45d3a725
[tune] Update trial resources on resume. ( #17975 )
...
Co-authored-by: Kai Fricke <kai@anyscale.com>
2021-08-27 09:12:18 +02:00
Eric Liang
d52ffd926e
Add task / actor name to driver log prefix ( #18105 )
...
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2021-08-26 16:18:04 -07:00
Edward Oakes
f16bb9849e
[serve] Update code sample in Ray README ( #18129 )
2021-08-26 16:34:31 -05:00
Edward Oakes
5c4c735119
[runtime_env] Make log message when deleting runtime_env INFO instead of ERROR ( #18083 )
2021-08-26 15:21:59 -05:00
Edward Oakes
6fa05ed708
[runtime_env] Better error message for working_dirs that exceed the max size ( #18092 )
2021-08-26 15:21:12 -05:00
Edward Oakes
3dc3f6102f
[serve] Remove unused ServeRequest codepath ( #18120 )
2021-08-26 15:08:00 -05:00
Dmitri Gekhtman
5608a4e441
fix ( #18123 )
2021-08-26 14:14:09 -04:00
Chen Shen
a7365b74e6
[CI][easy] run test_nested_id both inlined and from plasma store. ( #18081 )
2021-08-26 10:32:06 -07:00
SangBin Cho
405418f8e8
[Object Spilling] Unpin before updating URL ( #17994 )
...
* Unpin before updating URL
* Remove unnecessary logs.
* update compiling issue
* Check the consistent local state instead of stale information from obod.
* Fix the test
* Addressed code review.
2021-08-26 10:23:53 -07:00
architkulkarni
ea4f54f8ef
[Serve] [doc] Add model URI to deployment example ( #18085 )
2021-08-26 11:37:32 -05:00
Edward Oakes
c16e730f0e
[runtime_env] Better error message when ray client server fails to start ( #18088 )
2021-08-26 11:35:11 -05:00
Edward Oakes
83bfbf3b59
[runtime_env] Fix warning message to not say ray.connect() ( #18084 )
2021-08-26 11:34:44 -05:00
Edward Oakes
0c5f7a698d
[core] Add type hints to public APIs in worker.py ( #18049 )
2021-08-26 09:51:44 -05:00
Edward Oakes
07c05e16fa
[serve] Remove unused HTTP method metadata & matching ( #18079 )
2021-08-26 09:49:49 -05:00
Edward Oakes
0dd75c2f87
[serve] Skip namespace test in test_standalone on windows ( #18093 )
2021-08-26 09:48:30 -05:00
Kai Fricke
34cf5db109
[tune] Fix hyperopt points to evaluate for nested lists ( #18113 )
2021-08-26 14:34:22 +02:00
Sven Mika
8acb469b04
[RLlib; Testing] Green all RLlib nightly tests. ( #18073 )
2021-08-26 14:09:20 +02:00
Kai Fricke
089dd9b949
[release] Add release logs for 1.6.0 ( #18067 )
2021-08-26 12:13:15 +02:00
gjoliver
a8813675f4
[RLlib] Issue 17900: Set seed in single vectorized sub-envs properly, if num_envs_per_worker > 1 ( #18110 )
...
* In case a worker runs multiple envs, make sure a different seed can be deterministically set on all of them.
* Revert a couple of whitespace changes.
* Fix a few style errors.
Co-authored-by: Jun Gong <jungong@mbpro.local>
2021-08-26 11:32:58 +02:00
Raphael CHEN
edac59f18f
[tune] correctly validate initial points for random search ( #17282 )
...
Co-authored-by: Kai Fricke <kai@anyscale.com>
2021-08-26 10:24:51 +02:00
xwjiang2010
3fa20962cf
[Tune] Fix local mode. Add explicit concurrency limiter for local mode. ( #18023 )
...
Co-authored-by: Kai Fricke <krfricke@users.noreply.github.com>
2021-08-26 09:31:40 +02:00
Chen Shen
a29b157e2e
[core] better error message for lost objects ( #18068 )
2021-08-26 00:03:29 -07:00
Clark Zinzow
52bd0e1737
[Datasets] Drop empty tables when reading Parquet pieces. ( #18098 )
2021-08-26 00:02:08 -07:00
Eric Liang
e1f69ceb5e
Add documentation for DatasetPipeline.from_iterable ( #18106 )
2021-08-25 22:31:23 -07:00
Yi Cheng
f66c51de2d
[workflow] Support named step in workflow ( #17915 )
2021-08-25 19:51:45 -07:00
Clark Zinzow
ab0a638411
[Datasets] Add pyarrow minimum version check. ( #18082 )
2021-08-25 15:59:12 -07:00
Clark Zinzow
db1bdd28fc
Add pyarrow filesystem test coverage for Parquet reading. ( #18087 )
2021-08-25 15:58:57 -07:00
Tao Wang
15a7514cf6
[Core] Some request counts are missing in debug info ( #18069 )
2021-08-25 14:02:03 -07:00
Edward Oakes
406dc0b458
[core] Disallow empty string namespace + add validation tests ( #18048 )
2021-08-25 15:37:02 -05:00
Eric Liang
451c501bbd
[doc] Add API stability annotations to developer guide ( #18052 )
2021-08-25 13:34:43 -07:00
SangBin Cho
c2d488a504
[Usability] Add backpressure to log monitor ( #17774 )
...
* Add backpressure to log monitor
* Added a test and addressed code review.
* Addressed code review.
2021-08-25 13:07:18 -07:00
Sasha Sobol
fcb044d47c
[autoscaler] make 0 default min/max workers for head node ( #17757 )
...
* make 0 default min/max workers for head node
* fix helm charts, test, defaults for head
* fix test, docs
* make 0 default min/max workers for head node
* fix helm charts, test, defaults for head
* fix test, docs
* comments. logging
* better wording (logs)
Co-authored-by: Dmitri Gekhtman <62982571+DmitriGekhtman@users.noreply.github.com>
* fix logging message
* fix max workers in raycluster.yaml
* use default values of 0 for min/max workders in a helm chart
* add missing line back
Co-authored-by: Dmitri Gekhtman <62982571+DmitriGekhtman@users.noreply.github.com>
2021-08-25 14:56:20 -04:00
Jiao
b52c873027
[serve] Use list_deployments in benchmark ( #18050 )
2021-08-25 12:26:46 -05:00
Simon Mo
7c01ea7d2f
[Serve][Hotfix] Skip get_deployment on windows ( #18029 )
2021-08-25 11:27:31 -05:00
Simon Mo
ca61e43e76
[dashboard] Fix GCS retry error message in dashboard_head ( #18057 )
2021-08-25 11:23:36 -05:00
Edward Oakes
18ae99d8d8
[codeowners] Add @kombuchafox as code owner for dashboard snapshot ( #18051 )
2021-08-25 10:56:11 -05:00
Nikita Vemuri
a9c731edd3
[serve] Remove requirement to specify namespace for serve.start(detached=True) ( #17470 )
2021-08-25 10:39:32 -05:00
Kai Fricke
4c3276644e
[release] After buildkite ask step, use RAY_TEST_REPO pipeline ( #18074 )
2021-08-25 15:58:38 +02:00
