Skip to content

Fix Deployment model definition #271

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 21, 2024
Merged

Fix Deployment model definition #271

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
24 changes: 7 additions & 17 deletions replicate/deployment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,24 +79,14 @@ class Configuration(Resource):
The SKU for the hardware used to run the model.
"""

class Scaling(Resource):
"""
A scaling configuration for a deployment.
"""

min_instances: int
"""
The minimum number of instances for scaling.
"""

max_instances: int
"""
The maximum number of instances for scaling.
"""

scaling: Scaling
min_instances: int
"""
The scaling configuration for the deployment.
The minimum number of instances for scaling.
"""

max_instances: int
"""
The maximum number of instances for scaling.
"""

configuration: Configuration
Expand Down
23 changes: 14 additions & 9 deletions tests/test_deployment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,8 @@
},
"configuration": {
"hardware": "gpu-t4",
"scaling": {"min_instances": 1, "max_instances": 5},
"min_instances": 1,
"max_instances": 5,
},
},
},
Expand Down Expand Up @@ -86,7 +87,8 @@
},
"configuration": {
"hardware": "gpu-t4",
"scaling": {"min_instances": 1, "max_instances": 5},
"min_instances": 1,
"max_instances": 5,
},
},
},
Expand All @@ -105,7 +107,8 @@
},
"configuration": {
"hardware": "cpu",
"scaling": {"min_instances": 2, "max_instances": 10},
"min_instances": 2,
"max_instances": 10,
},
},
},
Expand Down Expand Up @@ -136,7 +139,8 @@
},
"configuration": {
"hardware": "gpu-t4",
"scaling": {"min_instances": 1, "max_instances": 5},
"min_instances": 1,
"max_instances": 5,
},
},
},
Expand Down Expand Up @@ -166,7 +170,8 @@
},
"configuration": {
"hardware": "gpu-v100",
"scaling": {"min_instances": 2, "max_instances": 10},
"min_instances": 2,
"max_instances": 10,
},
},
},
Expand Down Expand Up @@ -352,8 +357,8 @@ async def test_create_deployment(async_flag):
assert deployment.current_release.created_by.username == "acme"
assert deployment.current_release.created_by.name == "Acme, Inc."
assert deployment.current_release.configuration.hardware == "gpu-t4"
assert deployment.current_release.configuration.scaling.min_instances == 1
assert deployment.current_release.configuration.scaling.max_instances == 5
assert deployment.current_release.configuration.min_instances == 1
assert deployment.current_release.configuration.max_instances == 5


@respx.mock
Expand Down Expand Up @@ -392,5 +397,5 @@ async def test_update_deployment(async_flag):
assert updated_deployment.current_release.model == "acme/esrgan-updated"
assert updated_deployment.current_release.version == "new-version-id"
assert updated_deployment.current_release.configuration.hardware == "gpu-v100"
assert updated_deployment.current_release.configuration.scaling.min_instances == 2
assert updated_deployment.current_release.configuration.scaling.max_instances == 10
assert updated_deployment.current_release.configuration.min_instances == 2
assert updated_deployment.current_release.configuration.max_instances == 10