hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-08 11:31:40 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions
ray/release/serve_tests/serve_tests.yaml

102 lines
2 KiB
YAML
Raw Normal View History

[Serve] Add initial large scale tests (#17026)
2021-07-20 08:56:29 -07:00
- name: single_deployment_1k_noop_replica
[Test Infra] Unrevert team col (#21700) 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
2022-01-20 06:29:53 +09:00
team: serve
[Serve] Add initial large scale tests (#17026)
2021-07-20 08:56:29 -07:00
cluster:
app_config: app_config.yaml
[serve][release tests] Use m5.8xlarge instance types for 1k replica tests (#22918)
2022-03-08 21:34:01 -06:00
compute_template: compute_tpl_32_cpu.yaml
[Serve] Add initial large scale tests (#17026)
2021-07-20 08:56:29 -07:00
run:
[serve] Multi & single deployment large scale test (#17310)
2021-07-27 08:46:45 -07:00
timeout: 7200
[Serve] Add initial large scale tests (#17026)
2021-07-20 08:56:29 -07:00
long_running: False
[serve] Multi & single deployment large scale test (#17310)
2021-07-27 08:46:45 -07:00
script: python workloads/single_deployment_1k_noop_replica.py
Add micro benchmark to releaser repo (#17727)
2021-08-11 15:15:33 -07:00
[serve] Multi & single deployment large scale test (#17310)
2021-07-27 08:46:45 -07:00
smoke_test:
timeout: 600
- name: multi_deployment_1k_noop_replica
[Test Infra] Unrevert team col (#21700) 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
2022-01-20 06:29:53 +09:00
team: serve
[serve] Multi & single deployment large scale test (#17310)
2021-07-27 08:46:45 -07:00
cluster:
app_config: app_config.yaml
[serve][release tests] Use m5.8xlarge instance types for 1k replica tests (#22918)
2022-03-08 21:34:01 -06:00
compute_template: compute_tpl_32_cpu.yaml
[serve] Multi & single deployment large scale test (#17310)
2021-07-27 08:46:45 -07:00
run:
timeout: 7200
long_running: False
script: python workloads/multi_deployment_1k_noop_replica.py
Add micro benchmark to releaser repo (#17727)
2021-08-11 15:15:33 -07:00
smoke_test:
timeout: 600
[Serve] Serve Autoscaling Release tests (#21208)
2022-01-21 12:08:25 -08:00
- name: autoscaling_single_deployment
[Serve] Add "Serve" team tag to untagged release tests (#21861)
2022-01-25 11:46:03 -08:00
team: serve
[Serve] Serve Autoscaling Release tests (#21208)
2022-01-21 12:08:25 -08:00
cluster:
app_config: app_config.yaml
compute_template: compute_tpl_8_cpu_autoscaling.yaml
run:
timeout: 7200
long_running: False
script: python workloads/autoscaling_single_deployment.py
smoke_test:
timeout: 600
- name: autoscaling_multi_deployment
[Serve] Add "Serve" team tag to untagged release tests (#21861)
2022-01-25 11:46:03 -08:00
team: serve
[Serve] Serve Autoscaling Release tests (#21208)
2022-01-21 12:08:25 -08:00
cluster:
app_config: app_config.yaml
compute_template: compute_tpl_8_cpu_autoscaling.yaml
run:
timeout: 7200
long_running: False
script: python workloads/autoscaling_multi_deployment.py
smoke_test:
timeout: 600
Add micro benchmark to releaser repo (#17727)
2021-08-11 15:15:33 -07:00
- name: serve_micro_benchmark
[Test Infra] Unrevert team col (#21700) 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
2022-01-20 06:29:53 +09:00
team: serve
Add micro benchmark to releaser repo (#17727)
2021-08-11 15:15:33 -07:00
cluster:
app_config: app_config.yaml
[Serve] Add nightly test for Serve failure recovery (#19125)
2021-10-11 18:33:20 -07:00
# 16 CPUS
Add micro benchmark to releaser repo (#17727)
2021-08-11 15:15:33 -07:00
compute_template: compute_tpl_single_node.yaml
run:
timeout: 7200
long_running: False
script: python workloads/serve_micro_benchmark.py
[Serve] Add nightly test for Serve failure recovery (#19125)
2021-10-11 18:33:20 -07:00
smoke_test:
timeout: 600
[ci/release] use s3 sync (#21626) Previous changes failed because a) permission errors b) unzip being unavailable at remote nodes. Instead we are using tar gzip archives now. This reverts commit 42bcab27e83d135fce2ca40f06f47465daedd09e.
2022-01-15 17:53:19 -08:00
- name: serve_micro_benchmark_k8s
[Serve] Add "Serve" team tag to untagged release tests (#21861)
2022-01-25 11:46:03 -08:00
team: serve
[ci/release] use s3 sync (#21626) Previous changes failed because a) permission errors b) unzip being unavailable at remote nodes. Instead we are using tar gzip archives now. This reverts commit 42bcab27e83d135fce2ca40f06f47465daedd09e.
2022-01-15 17:53:19 -08:00
cluster:
app_config: app_config.yaml
# 16 CPUS
compute_template: compute_tpl_single_node_k8s.yaml
compute_on_k8s: True
run:
timeout: 7200
long_running: False
script: python workloads/serve_micro_benchmark.py
smoke_test:
timeout: 600
[Serve] Add nightly test for Serve failure recovery (#19125)
2021-10-11 18:33:20 -07:00
- name: serve_cluster_fault_tolerance
[Test Infra] Unrevert team col (#21700) 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
2022-01-20 06:29:53 +09:00
team: serve
[Serve] Add nightly test for Serve failure recovery (#19125)
2021-10-11 18:33:20 -07:00
cluster:
app_config: app_config.yaml
# 16 CPUS
compute_template: compute_tpl_single_node.yaml
run:
timeout: 7200
long_running: False
script: python workloads/serve_cluster_fault_tolerance.py
[Serve] Add initial large scale tests (#17026)
2021-07-20 08:56:29 -07:00
smoke_test:
[serve][release tests] Use m5.8xlarge instance types for 1k replica tests (#22918)
2022-03-08 21:34:01 -06:00
timeout: 600
Reference in a new issue Copy permalink