mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
b1308b1c8c
This fixes the previous problems from team column revert. This has 2 additional changes; alert handler receives the team argument, which was the root cause of breakage; https://github.com/ray-project/ray/pull/21289 Previously, tests without a team column were raising an exception, but I made the condition weaker (warning logs). I will eventually change it to raise an exception, but for smoother transition, we will log warning instead for a short time
49 lines
1.1 KiB
YAML
49 lines
1.1 KiB
YAML
- name: dask_xgboost_test
|
|
team: ml
|
|
cluster:
|
|
app_config: dask_xgboost_app_config.yaml
|
|
compute_template: compute_tpl.yaml
|
|
|
|
run:
|
|
use_connect: True
|
|
autosuspend_mins: 10
|
|
timeout: 1200
|
|
script: python workloads/dask_xgboost_test.py
|
|
args:
|
|
[
|
|
"--num-actors 4",
|
|
"--cpus-per-actor 4",
|
|
"--num-actors-inference 16",
|
|
"--cpus-per-actor-inference 1",
|
|
]
|
|
|
|
- name: modin_xgboost_test
|
|
team: ml
|
|
cluster:
|
|
app_config: modin_xgboost_app_config.yaml
|
|
compute_template: compute_tpl.yaml
|
|
|
|
run:
|
|
use_connect: True
|
|
autosuspend_mins: 10
|
|
timeout: 1200
|
|
script: python workloads/modin_xgboost_test.py
|
|
args:
|
|
[
|
|
"--num-actors 4",
|
|
"--cpus-per-actor 4",
|
|
"--num-actors-inference 16",
|
|
"--cpus-per-actor-inference 1",
|
|
]
|
|
|
|
- name: torch_tune_serve_test
|
|
team: ml
|
|
cluster:
|
|
app_config: torch_tune_serve_app_config.yaml
|
|
compute_template: gpu_tpl.yaml
|
|
|
|
run:
|
|
use_connect: True
|
|
autosuspend_mins: 10
|
|
timeout: 1200
|
|
script: python workloads/torch_tune_serve_test.py
|