mirror of
https://github.com/vale981/ray
synced 2025-03-08 19:41:38 -05:00
2c1fa459d4
* Add an RLlib Tune experiment to UserTest suite. * Add ray.init() * Move example script to example/tune/, so it can be imported as module. * add __init__.py so our new module will get included in python wheel. * Add block device to RLlib test instances. * Reduce disk size a little bit. * Add metrics reporting * Allow max of 5 workers to accomodate all the worker tasks. * revert disk size change. * Minor updates * Trigger build * set max num workers * Add a compute cfg for autoscaled cpu and gpu nodes. * use 1gpu instance. * install tblib for debugging worker crashes. * Manually upgrade to pytorch 1.9.0 * -y * torch=1.9.0 * install torch on driver * Add an RLlib Tune experiment to UserTest suite. * Add ray.init() * Move example script to example/tune/, so it can be imported as module. * add __init__.py so our new module will get included in python wheel. * Add block device to RLlib test instances. * Reduce disk size a little bit. * Add metrics reporting * Allow max of 5 workers to accomodate all the worker tasks. * revert disk size change. * Minor updates * Trigger build * set max num workers * Add a compute cfg for autoscaled cpu and gpu nodes. * use 1gpu instance. * install tblib for debugging worker crashes. * Manually upgrade to pytorch 1.9.0 * -y * torch=1.9.0 * install torch on driver * bump timeout * Write a more informational result dict. * Revert changes to compute config files that are not used. * add smoke test * update * reduce timeout * Reduce the # of env per worker to 1. * Small fix for getting trial_states * Trigger build * simply result dict * lint * more lint * fix smoke test Co-authored-by: Amog Kamsetty <amogkamsetty@yahoo.com>
38 lines
978 B
Python
38 lines
978 B
Python
"""Connect tests for Tune & RLlib.
|
|
|
|
Runs a couple of hard learning tests using Anyscale connect.
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
import time
|
|
|
|
import ray
|
|
from ray.rllib.examples.tune.framework import run
|
|
|
|
if __name__ == "__main__":
|
|
addr = os.environ.get("RAY_ADDRESS")
|
|
job_name = os.environ.get("RAY_JOB_NAME", "rllib_connect_tests")
|
|
if addr is not None and addr.startswith("anyscale://"):
|
|
ray.init(address=addr, job_name=job_name)
|
|
else:
|
|
ray.init(address="auto")
|
|
|
|
start_time = time.time()
|
|
exp_analysis = run()
|
|
end_time = time.time()
|
|
|
|
result = {
|
|
"time_taken": end_time - start_time,
|
|
"trial_states": {
|
|
t.config["framework"]: t.status
|
|
for t in exp_analysis.trials
|
|
},
|
|
}
|
|
|
|
test_output_json = os.environ.get("TEST_OUTPUT_JSON",
|
|
"/tmp/release_test_out.json")
|
|
with open(test_output_json, "wt") as f:
|
|
json.dump(result, f)
|
|
|
|
print("Ok.")
|