qbruntime.type.ModelConfig Class Reference#
|
SDK qb Runtime Library v1.2
MCS001-EN
|
Configures a core mode and core allocation of a model for NPU inference. More...
Public Member Functions | |
| __init__ (self, Optional[int] num_cores=None) | |
| Default constructor. | |
| bool | set_auto_core_mode (self) |
| Sets the model to detect CoreMode automatically. | |
| bool | set_single_core_mode (self, Optional[int] num_cores=None, Optional[List[CoreId]] core_ids=None) |
| Sets the model to use single-core mode for inference with a specified number of local cores. | |
| bool | set_global_core_mode (self, List[Cluster] clusters) |
| bool | set_global4_core_mode (self, List[Cluster] clusters=[Cluster.Cluster0, Cluster.Cluster1]) |
| Sets the model to use global4-core mode for inference with a specified set of NPU clusters. | |
| bool | set_global8_core_mode (self) |
| Sets the model to use global8-core mode for inference. | |
| CoreMode | get_core_mode (self) |
| Gets the core mode to be applied to the model. | |
| bool | set_multi_core_mode (self, List[Cluster] clusters=[Cluster.Cluster0, Cluster.Cluster1]) |
| Sets the model to use multi-core mode for batch inference. | |
| CoreAllocationPolicy | get_core_allocation_policy (self) |
| Gets the core allocation policy to be applied to the model. | |
| int | get_num_cores (self) |
| Gets the number of cores to be allocated for the model. | |
| bool | force_single_npu_bundle (self, int npu_bundle_index) |
| Forces the use of a specific NPU bundle. | |
| bool | get_forced_npu_bundle_index (self) |
| Retrieves the index of the forced NPU bundle. | |
| None | set_async_pipeline_enabled (self, bool enable) |
| Enables or disables the asynchronous pipeline required for asynchronous inference. | |
| bool | get_async_pipeline_enabled (self) |
| Returns whether the asynchronous pipeline is enabled in this configuration. | |
| None | set_activation_slots (self, int num) |
| Sets activation buffer slots for multi-activation supported model. | |
| int | get_activation_slots (self) |
| Returns activation buffer slot count. | |
| List[int] | early_latencies (self) |
| List[int] | finish_latencies (self) |
| early_latencies (self, List[int] latencies) | |
| finish_latencies (self, List[int] latencies) | |
| List[CoreId] | get_core_ids (self) |
| Returns the list of NPU CoreIds to be used for model inference. | |
| __repr__ (self) | |
Protected Attributes | |
| tuple | _model_config |
Detailed Description
Configures a core mode and core allocation of a model for NPU inference.
The ModelConfig class provides methods for setting a core mode and allocating cores for NPU inference. Supported core modes are single-core, multi-core, global4-core, and global8-core. Users can also specify which cores to allocate for the model. Additionally, the configuration offers an option to enforce the use of a specific NPU bundle.
- Note
- Deprecated functions are included for backward compatibility, but it is recommended to use the newer core mode configuration methods.
Constructor & Destructor Documentation
◆ __init__()
| qbruntime.type.ModelConfig.__init__ | ( | self, | |
| Optional[int] | num_cores = None ) |
Member Function Documentation
◆ set_auto_core_mode()
| bool qbruntime.type.ModelConfig.set_auto_core_mode | ( | self | ) |
Sets the model to detect CoreMode automatically.
In auto-core mode, the model automatically detects a supported CoreMode while using all available NPU cores.
- Note
- If the model has more than one CoreMode, CoreMode.Auto is not supported.
- activation buffer slots will be reset after set_auto_core_mode is called.
- Returns
- True if the mode was successfully set, False otherwise.
◆ set_single_core_mode()
| bool qbruntime.type.ModelConfig.set_single_core_mode | ( | self, | |
| Optional[int] | num_cores = None, | ||
| Optional[List[CoreId]] | core_ids = None ) |
Sets the model to use single-core mode for inference with a specified number of local cores.
In single-core mode, each local core executes model inference independently. The number of cores used is specified by the num_cores parameter, and the core allocation policy is set to CoreAllocationPolicy.Auto, meaning the model will be automatically allocated to available local cores when the model is launched to the NPU, specifically when the Model.launch() function is called. Or The user can specify a list of CoreIds to determine which cores to use for inference.
- Note
- Use exactly one of num_cores or core_ids, not both.
- Parameters
-
[in] num_cores The number of local cores to use for inference. [in] core_ids A list of CoreIds to be used for model inference.
- Returns
- True if the mode was successfully set, False otherwise.
◆ set_global_core_mode()
| bool qbruntime.type.ModelConfig.set_global_core_mode | ( | self, | |
| List[Cluster] | clusters ) |
◆ set_global4_core_mode()
| bool qbruntime.type.ModelConfig.set_global4_core_mode | ( | self, | |
| List[Cluster] | clusters = [Cluster.Cluster0, Cluster.Cluster1] ) |
Sets the model to use global4-core mode for inference with a specified set of NPU clusters.
For Aries NPU, there are two clusters, each consisting of four local cores. In global4-core mode, four local cores within the same cluster work together to execute the model inference.
- Parameters
-
[in] clusters A list of clusters to be used for model inference.
- Returns
- True if the mode was successfully set, False otherwise.
◆ set_global8_core_mode()
| bool qbruntime.type.ModelConfig.set_global8_core_mode | ( | self | ) |
Sets the model to use global8-core mode for inference.
For Aries NPU, there are two clusters, each consisting of four local cores. In global8-core mode, all eight local cores across the two clusters work together to execute the model inference.
- Returns
- True if the mode was successfully set, False otherwise.
◆ get_core_mode()
| CoreMode qbruntime.type.ModelConfig.get_core_mode | ( | self | ) |
◆ set_multi_core_mode()
| bool qbruntime.type.ModelConfig.set_multi_core_mode | ( | self, | |
| List[Cluster] | clusters = [Cluster.Cluster0, Cluster.Cluster1] ) |
Sets the model to use multi-core mode for batch inference.
In multi-core mode, on Aries NPU, the four local cores within a cluster work together to process batch inference tasks efficiently. This mode is optimized for batch processing.
- Parameters
-
[in] clusters A list of clusters to be used for multi-core batch inference.
- Returns
- True if the mode was successfully set, False otherwise.
◆ get_core_allocation_policy()
| CoreAllocationPolicy qbruntime.type.ModelConfig.get_core_allocation_policy | ( | self | ) |
Gets the core allocation policy to be applied to the model.
This reflects the core allocation policy that will be used when the model is created.
- Returns
- The CoreAllocationPolicy to be applied to the model.
◆ get_num_cores()
| int qbruntime.type.ModelConfig.get_num_cores | ( | self | ) |
◆ force_single_npu_bundle()
| bool qbruntime.type.ModelConfig.force_single_npu_bundle | ( | self, | |
| int | npu_bundle_index ) |
Forces the use of a specific NPU bundle.
This function forces the selection of a specific NPU bundle. If a non-negative index is provided, the corresponding NPU bundle is selected and runs without CPU offloading. If -1 is provided, all NPU bundles are used with CPU offloading enabled.
- Parameters
-
[in] npu_bundle_index The index of the NPU bundle to force. A non-negative integer selects a specific NPU bundle (runs without CPU offloading), or -1 to enable all NPU bundles with CPU offloading.
- Returns
- True if the index is valid and the NPU bundle is successfully set, False if the index is invalid (less than -1).
◆ get_forced_npu_bundle_index()
| bool qbruntime.type.ModelConfig.get_forced_npu_bundle_index | ( | self | ) |
Retrieves the index of the forced NPU bundle.
This function returns the index of the NPU bundle that has been forced using the force_single_npu_bundle function. If no NPU bundle is forced, the returned value will be -1.
- Returns
- The index of the forced NPU bundle, or -1 if no bundle is forced.
◆ set_async_pipeline_enabled()
| None qbruntime.type.ModelConfig.set_async_pipeline_enabled | ( | self, | |
| bool | enable ) |
Enables or disables the asynchronous pipeline required for asynchronous inference.
Call this function with enable set to True if you intend to use Model.infer_async(), as the asynchronous pipeline is necessary for their operation.
If you are only using synchronous inference, such as Model.infer() or Model.infer_to_float(), it is recommended to keep the asynchronous pipeline disabled to avoid unnecessary overhead.
- Parameters
-
[in] enable Set to True to enable the asynchronous pipeline; set to False to disable it.
◆ get_async_pipeline_enabled()
| bool qbruntime.type.ModelConfig.get_async_pipeline_enabled | ( | self | ) |
◆ set_activation_slots()
| None qbruntime.type.ModelConfig.set_activation_slots | ( | self, | |
| int | num ) |
Sets activation buffer slots for multi-activation supported model.
all this function if you want to set the number of activation buffer slots manually.
If you do not call this function, the default number of activation buffer slots is set differently depending on the CoreMode.
- CoreMode.Single : 2 * (the number of target core ids)
- CoreMode.Multi : 2 * (the number of target clusters)
- CoreMode.Global4 : 2 * (the number of target clusters)
- CoreMode.Global8 : 2
- Note
- This function has no effect on MXQ file in version earlier than MXQv7.
- Currently, LLM model's activation slot is fixed to 1 and ignoring count.
- Parameters
-
[in] count Multi activation counts. Must be >= 1.
◆ get_activation_slots()
| int qbruntime.type.ModelConfig.get_activation_slots | ( | self | ) |
◆ early_latencies() [1/2]
| List[int] qbruntime.type.ModelConfig.early_latencies | ( | self | ) |
◆ finish_latencies() [1/2]
| List[int] qbruntime.type.ModelConfig.finish_latencies | ( | self | ) |
◆ early_latencies() [2/2]
| qbruntime.type.ModelConfig.early_latencies | ( | self, | |
| List[int] | latencies ) |
- Deprecated
- This setting has no effect.
◆ finish_latencies() [2/2]
| qbruntime.type.ModelConfig.finish_latencies | ( | self, | |
| List[int] | latencies ) |
- Deprecated
- This setting has no effect.
◆ get_core_ids()
| List[CoreId] qbruntime.type.ModelConfig.get_core_ids | ( | self | ) |
Returns the list of NPU CoreIds to be used for model inference.
This function returns a list of NPU CoreIds that the model will use for inference. When set_single_core_mode(num_cores) is called and the core allocation policy is set to CoreAllocationPolicy.Auto, it will return an empty list.
- Returns
- A list of NPU CoreIds.
◆ __repr__()
Member Data Documentation
◆ _model_config
|
protected |
The documentation for this class was generated from the following file:
Generated by
1.14.0