Skip to content

fix(ray): align autoscale config #263

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 11, 2025
Merged

fix(ray): align autoscale config #263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions instill/helpers/const.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,7 @@ class ImageToImageInput:
"num_cpus": 0,
}
DEFAULT_AUTOSCALING_CONFIG = {
"target_num_ongoing_requests_per_replica": 2,
"target_ongoing_requests": 2,
"initial_replicas": 1,
"min_replicas": 0,
Expand All @@ -124,8 +125,8 @@ class ImageToImageInput:
"PYTHONPATH": os.getcwd(),
},
}
DEFAULT_MAX_ONGOING_REQUESTS = 5
DEFAULT_MAX_QUEUED_REQUESTS = 10
DEFAULT_MAX_ONGOING_REQUESTS = 6
DEFAULT_MAX_QUEUED_REQUESTS = 100

RAM_MINIMUM_RESERVE = 1 # GB
RAM_UPSCALE_FACTOR = 1.25
Expand Down
3 changes: 3 additions & 0 deletions instill/helpers/ray_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,9 @@ def __init__(self, deployable: Deployment) -> None:

is_test_model = os.getenv(ENV_IS_TEST_MODEL)
if is_test_model is not None and is_test_model.lower() == "true":
self._update_max_replicas(1000)
self._update_num_cpus(float(0.001))
self._update_upscale_delay(30)
self._update_downscale_delay(60)

is_high_scale_model = os.getenv(ENV_IS_HIGH_SCALE_MODEL)
Expand Down Expand Up @@ -205,5 +207,6 @@ def instill_deployment(
ray_actor_options=DEFAULT_RAY_ACTOR_OPTIONS,
autoscaling_config=DEFAULT_AUTOSCALING_CONFIG,
max_ongoing_requests=DEFAULT_MAX_ONGOING_REQUESTS,
max_concurrent_queries=DEFAULT_MAX_ONGOING_REQUESTS,
max_queued_requests=DEFAULT_MAX_QUEUED_REQUESTS,
)