-
Notifications
You must be signed in to change notification settings - Fork 829
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.
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
Fixed the priority of parameters defined in register curl cmd vs model-config.yaml #2858
Merged
Merged
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,142 @@ | ||
| import shutil | ||
| from pathlib import Path | ||
| from unittest.mock import patch | ||
|
|
||
| import pytest | ||
| import test_utils | ||
| from model_archiver import ModelArchiverConfig | ||
|
|
||
| CURR_FILE_PATH = Path(__file__).parent | ||
| REPO_ROOT_DIR = CURR_FILE_PATH.parent.parent | ||
|
|
||
| MODEL_PY = """ | ||
| import torch | ||
| import torch.nn as nn | ||
|
|
||
| class Foo(nn.Module): | ||
| def __init__(self): | ||
| super().__init__() | ||
|
|
||
| def forward(self, x): | ||
| return x | ||
| """ | ||
|
|
||
| HANDLER_PY = """ | ||
| import os | ||
| import torch | ||
| from ts.torch_handler.base_handler import BaseHandler | ||
|
|
||
| class FooHandler(BaseHandler): | ||
| def initialize(self, ctx): | ||
| super().initialize(ctx) | ||
|
|
||
| def preprocess(self, data): | ||
| return torch.as_tensor(int(data[0].get('body').decode('utf-8')), device=self.device) | ||
|
|
||
| def postprocess(self, x): | ||
| return [x.item()] | ||
| """ | ||
|
|
||
| MODEL_CONFIG_YAML = f""" | ||
| #frontend settings | ||
| # TorchServe frontend parameters | ||
| minWorkers: 1 | ||
| maxWorkers: 4 | ||
| maxBatchDelay: 100 | ||
| batchSize: 4 | ||
| """ | ||
|
|
||
|
|
||
| @pytest.fixture(scope="module") | ||
| def model_name(): | ||
| yield "foo" | ||
|
|
||
|
|
||
| @pytest.fixture(scope="module") | ||
| def work_dir(tmp_path_factory, model_name): | ||
| return Path(tmp_path_factory.mktemp(model_name)) | ||
|
|
||
|
|
||
| @pytest.fixture(scope="module", name="mar_file_path") | ||
| def create_mar_file(work_dir, model_archiver, model_name): | ||
| mar_file_path = work_dir.joinpath(model_name + ".mar") | ||
|
|
||
| model_config_yaml_file = work_dir / "model_config.yaml" | ||
| model_config_yaml_file.write_text(MODEL_CONFIG_YAML) | ||
|
|
||
| model_py_file = work_dir / "model.py" | ||
| model_py_file.write_text(MODEL_PY) | ||
|
|
||
| handler_py_file = work_dir / "handler.py" | ||
| handler_py_file.write_text(HANDLER_PY) | ||
|
|
||
| config = ModelArchiverConfig( | ||
| model_name=model_name, | ||
| version="1.0", | ||
| serialized_file=None, | ||
| model_file=model_py_file.as_posix(), | ||
| handler=handler_py_file.as_posix(), | ||
| extra_files=None, | ||
| export_path=work_dir, | ||
| requirements_file=None, | ||
| runtime="python", | ||
| force=False, | ||
| archive_format="default", | ||
| config_file=model_config_yaml_file.as_posix(), | ||
| ) | ||
|
|
||
| with patch("archiver.ArgParser.export_model_args_parser", return_value=config): | ||
| model_archiver.generate_model_archive() | ||
|
|
||
| assert mar_file_path.exists() | ||
|
|
||
| yield mar_file_path.as_posix() | ||
|
|
||
| # Clean up files | ||
| mar_file_path.unlink(missing_ok=True) | ||
|
|
||
|
|
||
| def register_model(mar_file_path, model_store, params, torchserve): | ||
| shutil.copy(mar_file_path, model_store) | ||
|
|
||
| file_name = Path(mar_file_path).name | ||
|
|
||
| model_name = Path(file_name).stem | ||
|
|
||
| params = params + ( | ||
| ("model_name", model_name), | ||
| ("url", file_name), | ||
| ) | ||
|
|
||
| test_utils.reg_resp = test_utils.register_model_with_params(params) | ||
| return model_name | ||
|
|
||
|
|
||
| def test_register_model_with_batch_size(mar_file_path, model_store, torchserve): | ||
| params = ( | ||
| ("initial_workers", "2"), | ||
| ("synchronous", "true"), | ||
| ("batch_size", "2"), | ||
| ) | ||
|
|
||
| model_name = register_model(mar_file_path, model_store, params, torchserve) | ||
|
|
||
| describe_resp = test_utils.describe_model(model_name, "1.0") | ||
|
|
||
| assert describe_resp[0]["batchSize"] == 2 | ||
|
|
||
| test_utils.unregister_model(model_name) | ||
|
|
||
|
|
||
| def test_register_model_without_batch_size(mar_file_path, model_store, torchserve): | ||
| params = ( | ||
| ("initial_workers", "2"), | ||
| ("synchronous", "true"), | ||
| ) | ||
| model_name = register_model(mar_file_path, model_store, params, torchserve) | ||
|
|
||
| describe_resp = test_utils.describe_model(model_name, "1.0") | ||
|
|
||
| assert describe_resp[0]["batchSize"] == 4 | ||
|
|
||
| test_utils.unregister_model(model_name) |
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
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: Do we need this? Can't we achieve the same with
json?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
According to the description, it is fastest json lib. I'm thinking if we need apply orjson in our handler for json input.