mirror of
https://github.com/wassname/ray.git
synced 2026-07-11 23:08:38 +08:00
Richard Liaw
784a6399b0
This PR introduces single-node fault tolerance for Tune. ## Previous behavior: - Actors will be restarted without checking if resources are available. This can lead to problems if we lose resources. ## New behavior: - RUNNING trials will be resumed on another node on a best effort basis (meaning they will run if resources available). - If the cluster is saturated, RUNNING trials on that failed node will become PENDING and queued. - During recovery, TrialSchedulers and SearchAlgorithms should receive notification of this (via `trial_runner.stop_trial`) so that they don’t wait/block for a trial that isn’t running. Remaining questions: - Should `last_result` be consistent during restore? Yes; but not for earlier trials (trials that are yet to be checkpointed). - Waiting for some PRs to merge first (#3239) Closes #2851.
Ray
===
.. image:: https://travis-ci.com/ray-project/ray.svg?branch=master
:target: https://travis-ci.com/ray-project/ray
.. image:: https://readthedocs.org/projects/ray/badge/?version=latest
:target: http://ray.readthedocs.io/en/latest/?badge=latest
|
Ray is a flexible, high-performance distributed execution framework.
Ray is easy to install: ``pip install ray``
Example Use
-----------
+------------------------------------------------+----------------------------------------------------+
| **Basic Python** | **Distributed with Ray** |
+------------------------------------------------+----------------------------------------------------+
|.. code-block:: python |.. code-block:: python |
| | |
| # Execute f serially. | # Execute f in parallel. |
| | |
| | @ray.remote |
| def f(): | def f(): |
| time.sleep(1) | time.sleep(1) |
| return 1 | return 1 |
| | |
| | |
| | ray.init() |
| results = [f() for i in range(4)] | results = ray.get([f.remote() for i in range(4)]) |
+------------------------------------------------+----------------------------------------------------+
Ray comes with libraries that accelerate deep learning and reinforcement learning development:
- `Ray Tune`_: Hyperparameter Optimization Framework
- `Ray RLlib`_: Scalable Reinforcement Learning
- `Distributed Training <http://ray.readthedocs.io/en/latest/distributed_sgd.html>`__
.. _`Ray Tune`: http://ray.readthedocs.io/en/latest/tune.html
.. _`Ray RLlib`: http://ray.readthedocs.io/en/latest/rllib.html
Installation
------------
Ray can be installed on Linux and Mac with ``pip install ray``.
To build Ray from source or to install the nightly versions, see the `installation documentation`_.
.. _`installation documentation`: http://ray.readthedocs.io/en/latest/installation.html
More Information
----------------
- `Documentation`_
- `Tutorial`_
- `Blog`_
- `Ray paper`_
- `Ray HotOS paper`_
.. _`Documentation`: http://ray.readthedocs.io/en/latest/index.html
.. _`Tutorial`: https://github.com/ray-project/tutorial
.. _`Blog`: https://ray-project.github.io/
.. _`Ray paper`: https://arxiv.org/abs/1712.05889
.. _`Ray HotOS paper`: https://arxiv.org/abs/1703.03924
Getting Involved
----------------
- Ask questions on our mailing list `ray-dev@googlegroups.com`_.
- Please report bugs by submitting a `GitHub issue`_.
- Submit contributions using `pull requests`_.
.. _`ray-dev@googlegroups.com`: https://groups.google.com/forum/#!forum/ray-dev
.. _`GitHub issue`: https://github.com/ray-project/ray/issues
.. _`pull requests`: https://github.com/ray-project/ray/pulls