Add timeout parameter as optional for isvc creation and it corresponding change #135
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Tarun Kumar <[email protected]>
|
The following are automatically added/executed:
Available user actions:
Supported labels{'/wip', '/lgtm', '/hold', '/verified'} |
for more information, see https://pre-commit.ci
|
/verified |
rnetser
requested changes
Feb 10, 2025
| @@ -34,22 +33,25 @@ | |||
| LOGGER = get_logger(name=__name__) | |||
|
|
|||
|
|
|||
| def verify_no_failed_pods(client: DynamicClient, isvc: InferenceService, runtime_name: str | None) -> None: | |||
| def verify_no_failed_pods( | |||
| client: DynamicClient, isvc: InferenceService, runtime_name: str | None, timeout: int = 5 * 60 | |||
There was a problem hiding this comment.
please use TIMEOUT_5MIN from constants
utilities/infra.py
Outdated
| @@ -88,6 +88,7 @@ def wait_for_inference_deployment_replicas( | |||
| isvc: InferenceService, | |||
| runtime_name: str | None, | |||
| expected_num_deployments: int = 1, | |||
| timeout: int = 4 * 60, | |||
There was a problem hiding this comment.
please save to constants and re-use (also in create_ns)
adolfo-ab
previously approved these changes
Feb 10, 2025
| @@ -34,22 +33,25 @@ | |||
| LOGGER = get_logger(name=__name__) | |||
|
|
|||
|
|
|||
| def verify_no_failed_pods(client: DynamicClient, isvc: InferenceService, runtime_name: str | None) -> None: | |||
| def verify_no_failed_pods( | |||
| client: DynamicClient, isvc: InferenceService, runtime_name: str | None, timeout: int = 5 * 60 | |||
utilities/infra.py
Outdated
| @@ -88,6 +88,7 @@ def wait_for_inference_deployment_replicas( | |||
| isvc: InferenceService, | |||
| runtime_name: str | None, | |||
| expected_num_deployments: int = 1, | |||
| timeout: int = 4 * 60, | |||
| @@ -125,6 +127,7 @@ def create_isvc( | |||
| wait_for_predictor_pods: bool = True, | |||
| autoscaler_mode: Optional[str] = None, | |||
| multi_node_worker_spec: Optional[dict[str, int]] = None, | |||
| timeout: int = 15 * 60, | |||
Signed-off-by: Tarun Kumar <[email protected]>
github-actions
bot
added
size/l
and removed
size/s
Verified
|
closing this the branch is messed up |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I observed that when testing a larger model, which takes more time to download, the default timeout parameter isn't sufficient, causing the model deployment to fail. As a result, I modified the timeout parameter to be an option in the inference function, allowing for easier control.