Main process manages models, child process loads models. #16850
Conversation
This file contains hidden or 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
…agement # Conflicts: # iotdb-core/ainode/iotdb/ainode/core/config.py # iotdb-core/ainode/iotdb/ainode/core/constant.py # iotdb-core/ainode/iotdb/ainode/core/exception.py # iotdb-core/ainode/iotdb/ainode/core/inference/pipeline/__init__.py # iotdb-core/ainode/iotdb/ainode/core/inference/pipeline/basic_pipeline.py # iotdb-core/ainode/iotdb/ainode/core/inference/pipeline/pipeline_loader.py # iotdb-core/ainode/iotdb/ainode/core/manager/inference_manager.py # iotdb-core/ainode/iotdb/ainode/core/manager/model_manager.py # iotdb-core/ainode/iotdb/ainode/core/model/model_info.py # iotdb-core/ainode/iotdb/ainode/core/model/model_storage.py # iotdb-core/ainode/iotdb/ainode/core/model/utils.py # iotdb-core/ainode/iotdb/ainode/core/rpc/handler.py
…agement # Conflicts: # iotdb-core/ainode/iotdb/ainode/core/model/model_constants.py
RkGrit force-pushed the model-management branch from 07f4d73 to 611dfe7 Compare Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
2 participants
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 Outdated suggestions cannot be applied.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.
The InferenceRequestPool subprocess no longer loads the model through the ModelManager instance, but directly calls the load_model method, and the parameter passed to it is model_info instead of model_storage.
In this way, ModelManager and ModelStorage are only controlled by the main process, but it is not responsible for loading the model. During inference, the InferenceRequestPool subprocess loads the model as needed through the Pipeline.
Final effect: Main process manages models, child process loads models.