sparseml.framework package¶
Submodules¶
sparseml.framework.info module¶
Functionality related to integrating with, detecting, and getting information for support and sparsification in ML frameworks.
The file is executable and will get the framework info for a given framework:
Compile the available setup and information for a given framework.
- positional arguments:
- framework the ML framework or path to a framework file to load the
framework info for
- optional arguments:
- -h, --help
show this help message and exit
- --path PATH
A full file path to save the framework info to. If not supplied, will print out the framework info to the console.
-
class
sparseml.framework.info.
FrameworkInferenceProviderInfo
(*, name: str, description: str, device: str, supported_sparsification: sparseml.sparsification.info.SparsificationInfo = None, available: bool = False, properties: Dict[str, Any] = {}, warnings: List[str] = [])[source]¶ Bases:
pydantic.main.BaseModel
Class for storing information for an inference provider within a frameworks engine. For example, the gpu provider within PyTorch. Extends pydantics BaseModel class for serialization to and from json in addition to proper type checking on construction.
-
available
: bool¶
-
description
: str¶
-
device
: str¶
-
name
: str¶
-
properties
: Dict[str, Any]¶
-
supported_sparsification
: Optional[sparseml.sparsification.info.SparsificationInfo]¶
-
warnings
: List[str]¶
-
-
class
sparseml.framework.info.
FrameworkInfo
(*, framework: sparseml.base.Framework, package_versions: Dict[str, Optional[str]], sparsification: sparseml.sparsification.info.SparsificationInfo = None, inference_providers: List[sparseml.framework.info.FrameworkInferenceProviderInfo] = [], properties: Dict[str, Any] = {}, training_available: bool = False, sparsification_available: bool = False, exporting_onnx_available: bool = False, inference_available: bool = False)[source]¶ Bases:
pydantic.main.BaseModel
Class for storing the information for an ML frameworks info and availability on the current system. Extends pydantics BaseModel class for serialization to and from json in addition to proper type checking on construction.
-
exporting_onnx_available
: bool¶
-
framework
: sparseml.base.Framework¶
-
inference_available
: bool¶
-
inference_providers
: List[sparseml.framework.info.FrameworkInferenceProviderInfo]¶
-
package_versions
: Dict[str, Optional[str]]¶
-
properties
: Dict[str, Any]¶
-
sparsification
: Optional[sparseml.sparsification.info.SparsificationInfo]¶
-
sparsification_available
: bool¶
-
training_available
: bool¶
-
-
sparseml.framework.info.
framework_info
(framework: Any) → sparseml.framework.info.FrameworkInfo[source]¶ Detect the information for the given ML framework such as package versions, availability for core actions such as training and inference, sparsification support, and inference provider support.
- Parameters
framework (Any) – The item to detect the ML framework for. See
detect_framework()
for more information.- Returns
The framework info for the given framework
- Return type
-
sparseml.framework.info.
load_framework_info
(load: str) → sparseml.framework.info.FrameworkInfo[source]¶ Load the framework info from a file or raw json. If load exists as a path, will read from the file and use that. Otherwise will try to parse the input as a raw json str.
- Parameters
load (str) – Either a file path to a json file or a raw json string.
- Returns
The loaded framework info.
- Return type
-
sparseml.framework.info.
save_framework_info
(framework: Any, path: Optional[str] = None)[source]¶ Save the framework info for a given framework. If path is provided, will save to a json file at that path. If path is not provided, will print out the info.
- Parameters
framework (Any) – The item to detect the ML framework for. See
detect_framework()
for more information.path (Optional[str]) – The path, if any, to save the info to in json format. If not provided will print out the info.
Module contents¶
Functionality related to integrating with, detecting, and getting information for support and sparsification in ML frameworks.