mirror of
https://github.com/vale981/ray
synced 2025-03-12 06:06:39 -04:00
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
72 lines
No EOL
1.4 KiB
YAML
72 lines
No EOL
1.4 KiB
YAML
- name: single_deployment_1k_noop_replica
|
|
team: serve
|
|
cluster:
|
|
app_config: app_config.yaml
|
|
compute_template: compute_tpl_8_cpu.yaml
|
|
|
|
run:
|
|
timeout: 7200
|
|
long_running: False
|
|
script: python workloads/single_deployment_1k_noop_replica.py
|
|
|
|
smoke_test:
|
|
timeout: 600
|
|
|
|
- name: multi_deployment_1k_noop_replica
|
|
team: serve
|
|
cluster:
|
|
app_config: app_config.yaml
|
|
compute_template: compute_tpl_8_cpu.yaml
|
|
|
|
run:
|
|
timeout: 7200
|
|
long_running: False
|
|
script: python workloads/multi_deployment_1k_noop_replica.py
|
|
|
|
smoke_test:
|
|
timeout: 600
|
|
|
|
- name: serve_micro_benchmark
|
|
team: serve
|
|
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_micro_benchmark.py
|
|
|
|
smoke_test:
|
|
timeout: 600
|
|
|
|
- name: serve_micro_benchmark_k8s
|
|
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
|
|
|
|
- name: serve_cluster_fault_tolerance
|
|
team: serve
|
|
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
|
|
|
|
smoke_test:
|
|
timeout: 600 |