API Reference

Mobilint SDK qb Compiler v1.0 MCS002-EN

Classes | Functions | Variables

API Reference

Mobilint qb Compiler API provides functions for compiling models from various framework(onnx, pytorch, transformers, etc.) to MXQ format. More...

Classes
class	qbcompiler.frontend.Model_Dict
	Wrapper around the Mobilint compiler to support compilation and inference workflows. More...
class	qbcompiler.calibration.preprocess.GetNpy
	Load NumPy data from an in-memory array or a .npy file. More...
class	qbcompiler.calibration.preprocess.NpyNormalize
class	qbcompiler.calibration.preprocess.NpyPad
	Pad NumPy arrays to a desired shape. More...
class	qbcompiler.calibration.preprocess.GetImage
	Retrieve an image tensor from a file path or NumPy array using OpenCV. More...
class	qbcompiler.calibration.preprocess.Pad
	Pad images to a target shape or to meet a size divisor. More...
class	qbcompiler.calibration.preprocess.Normalize
	Apply mean/std normalization to images. More...
class	qbcompiler.calibration.preprocess.ResizeTorch
class	qbcompiler.calibration.preprocess.Resize
	Resize images with optional aspect-ratio preservation. More...
class	qbcompiler.calibration.preprocess.CenterCrop
	Perform a centered crop on the image. More...
class	qbcompiler.calibration.preprocess.SetOrder
class	qbcompiler.calibration.preprocess.preproc_builder
	Build a calibration preprocessing pipeline from a YAML or dict configuration. More...
class	GetText
	Extract text strings from raw inputs. More...
class	TokenizeToEmbedding
	Convert tokenized text into embeddings using a Hugging Face model. More...
class	YoloPre
	Apply YOLO-style resize, padding, and normalization to images. More...

Functions
	qbcompiler.frontend.mxq_compile (model, str calib_data_path="", int save_subgraph_type=0, output_subgraph_path="", str model_nickname=None, str save_path=None, backend="onnx", device="cpu", feed_dict=None, dynamic_axes=None, in_dformats=None, save_sample=False, inference_scheme="single", yolo_decode_include=False, use_random_calib=False, cpu_offload=False, optimize_option=1, sample_dtype="float", buffer_mode=1, input_shape_dict=dict(), use_custom_mask=False, exclude_first_subgraph=False, Optional[CompileConfig] compile_config=None, Optional[ResourceManagementConfig] resource_management_config=None, Optional[QuantizationConfig] quantization_config=None, Optional[AdvancedQuantizationConfig] advanced_quantization_config=None, Optional[LlmConfig] llm_config=None, Optional[InputProcessConfig] input_process_config=None, **kwargs)
	Compile a model into a Mobilint eXeCUtable (MXQ) package for execution on Mobilint NPUs.
	qbcompiler.frontend.mblt_compile (str|Any model, str mblt_save_path, backend="onnx", device="cpu", feed_dict=None, dynamic_axes=None, in_dformats=None, yolo_decode_include=False, cpu_offload=False, use_custom_mask=False, exclude_first_subgraph=False, **kwargs)
	Export a model to the Mobilint .mblt format without producing an MXQ package.
	qbcompiler.frontend.run_mblt_model (str path_to_mblt, bool save_all_outputs=True, Optional[str] inference_output_path=None, Optional[int] target_subgraph=None)
	qbcompiler.calibration.make_calib_data.get_yaml (str yaml_path)
	qbcompiler.calibration.make_calib_data.make_calib_man (pre_ftn, str data_dir, str save_dir, str save_name, str anno_json=None, str file_format="%012d.jpg", int max_size=-1, bool remove_npy=False, int seed=2023, bool save_calib_msg=False, str msg_path=None)
	From images and a user-provided preprocessing function, generate calibration NumPy files and a manifest.
str	qbcompiler.calibration.make_calib_data.make_calib (Union[str, dict] args_pre, str data_dir, str save_dir, str save_name=None, str anno_json=None, str file_format="%012d.jpg", int max_size=-1, bool remove_npy=False, int seed=2023, bool save_calib_msg=False, str msg_path=None)
	Create calibration NumPy files and a manifest using a YAML or dict preprocessing configuration.
List[str]	qbcompiler.calibration.make_calib_data.make_calib_llm (Union[str, dict] args_pre, str dataset_name, Union[List[str], str] subset_list, str text_field, str split, str save_dir, int max_calib=512, Optional[str] save_prefix=None)
	Generate calibration embeddings for LLM models using Hugging Face datasets.
	qbcompiler.calibration.preprocess.preprocess_fnc (fnc, Datatype="Image")

Variables
dict	qbcompiler.calibration.preprocess.DTYPE_GETDATA_MAP = {"Image": "GetImage", "Npy": "GetNpy", "LLM": "GetText"}

Detailed Description

Mobilint qb Compiler API provides functions for compiling models from various framework(onnx, pytorch, transformers, etc.) to MXQ format.

Function Documentation

◆ mxq_compile()

qbcompiler.frontend.mxq_compile	(		model,
		str	calib_data_path = "",
		int	save_subgraph_type = 0,
			output_subgraph_path = "",
		str	model_nickname = None,
		str	save_path = None,
			backend = "onnx",
			device = "cpu",
			feed_dict = None,
			dynamic_axes = None,
			in_dformats = None,
			save_sample = False,
			inference_scheme = "single",
			yolo_decode_include = False,
			use_random_calib = False,
			cpu_offload = False,
			optimize_option = 1,
			sample_dtype = "float",
			buffer_mode = 1,
			input_shape_dict = dict(),
			use_custom_mask = False,
			exclude_first_subgraph = False,
		Optional[CompileConfig]	compile_config = None,
		Optional[ResourceManagementConfig]	resource_management_config = None,
		Optional[QuantizationConfig]	quantization_config = None,
		Optional[AdvancedQuantizationConfig]	advanced_quantization_config = None,
		Optional[LlmConfig]	llm_config = None,
		Optional[InputProcessConfig]	input_process_config = None,
		**	kwargs )

Compile a model into a Mobilint eXeCUtable (MXQ) package for execution on Mobilint NPUs.

Parameters

model	string or model instance. Model path. When using backend="onnx", this should be the path to an ONNX model file. When backend is "torchscript", provide a TorchScript module; when "torch", provide a standard PyTorch model. For backend="tf", pass the directory that contains the TensorFlow SavedModel graph and assets. For backend="tflite", pass the TF Lite model path.
calib_data_path	string. Path to the calibration dataset. Accepts either a text/json file that lists NumPy files or a directory that contains the pre-processed NumPy files.
save_subgraph_type	int. Controls optional MBLT subgraph exports: 0 disables exports; 1 saves only the graph structure; 2 saves graph structure plus weights; 3 saves the graph structure split into multiple subgraphs; 4 saves both structure and weights split into multiple subgraphs.
output_subgraph_path	string. Destination path for the exported .mblt file when save_subgraph_type is 1, 2, 3, or 4. The resulting file can be used for visualization.
model_nickname	string. Friendly name stored in qbcompiler. Defaults to the model basename (for example, the file "/workspace/onnx/resnet50.onnx" becomes "resnet50"). Falls back to "temporary" when it cannot be inferred.
save_path	string. Output MXQ filename. Defaults to "{model_nickname}.mxq" when omitted.
backend	string. Framework used to generate the Mobilint IR. Must be one of "onnx", "tf", "tflite", "torchscript", or "torch". Defaults to "onnx".
device	string. Compilation and inference device: "cpu" or "gpu". Defaults to "cpu".
feed_dict	dict. Example input tensors for shape inference and inference validation.
dynamic_axes	dict. Marks model axes as dynamic. Keys are input names and values map dimension indices to aliases (for example {"input": {2: "seq_len"}}).
in_dformats	dict. Describes input tensor data formats.
save_sample	bool. Stores input/output tensors in ./sampleInOut when True to aid debugging. Defaults to False.
inference_scheme	string. NPU inference scheme. One of "single", "multi", "global", "global4", or "global8".
yolo_decode_include	bool. Determines whether YOLO decode runs on NPU.
use_random_calib	bool. Generates random calibration data to validate model compilability. Defaults to False.
cpu_offload	bool. Enables CPU offloading during NPU inference. Defaults to False.
optimize_option	int. Compiler optimization strategy selector.
sample_dtype	string. Data type for saved sample inference outputs: "float" or "int8".
buffer_mode	int. Buffer serialization mode: 0 uses a naïve buffer, 1 uses an mmap-backed buffer. Defaults to 1.
input_shape_dict:multi-shape	compilation specification for STT/TTS models only (e.g., Conformer-CTC, MeloTTS). The dynamic axis is defined with respect to each input tensor’s shape. During compilation, the same axis is varied across all model inputs using the provided values. Currently, only a single entry key ("multi_shape0") is supported. Example: {"multi_shape0": {"axis": 2, "values": [100, 200, 300]}}
use_custom_mask	bool. For non-LLM models that include a mask, use a custom mask provided as a separate input instead of the causal mask. For LLMs that incorporate RoPE, setting LLMConfig.dynamic_rope to True not only enables the use of dynamic RoPE provided via an additional input, but also activates the custom mask.
exclude_first_subgraph	bool. Applies only when CPU offloading is enabled: exclude the first subgraph from the final graph if it is unsupported.
compile_config	string. Path to JSON configuration file containing all quantization-related settings (resourceManagement, quantization, advancedQuantization, llmConfig). If provided, this takes precedence over individual sub-config parameters.
resource_management_config	ResourceManagementConfig. Resource management configuration object.
quantization_config	QuantizationConfig. Quantization configuration object.
advanced_quantization_config	AdvancedQuantizationConfig. Advanced quantization configuration object.
llm_config	LlmConfig. LLM configuration object.
input_process_config	InputProcessConfig. Unified input processing configuration containing uint8 input handling, image channels, and preprocessing pipeline settings.
kwargs	dict. Additional compiler arguments propagated to the backend implementation. Moreover, If you want to override only a subset of configuration values, you can pass them to mxq_compile as keyword arguments (kwargs), and they will be applied. Note that AdvancedQuantizationConfig and its sub-configurations are not updated automatically from kwargs. In contrast, ResourceManagementConfig, QuantizationConfig, and LlmConfig support automatic updates via each configuration class’s from_kwargs method. See Example 3 below for a usage example.

Returns

None.

Using configuration

There are two ways to configure quantization settings:

1. Load all settings from a JSON config file:
   from qbcompiler import mxq_compile

   mxq_compile(

   model="path/to/model.onnx",

   calib_data_path="path/to/calib",

   compile_config="path/to/config.json",

   device="gpu",

   )
2. Pass individual sub-config objects:
   from qbcompiler import mxq_compile

   from qbcompiler.configs import (

   ResourceManagementConfig,

   QuantizationConfig,

   AdvancedQuantizationConfig,

   LlmConfig,

   )

   resource_mgmt = ResourceManagementConfig(weight_dtype="float32")

   quant_cfg = QuantizationConfig(...)

   adv_quant_cfg = AdvancedQuantizationConfig(...)

   llm_cfg = LlmConfig(...)

   mxq_compile(

   model="path/to/model.onnx",

   calib_data_path="path/to/calib",

   resource_management_config=resource_mgmt,

   quantization_config=quant_cfg,

   advanced_quantization_config=adv_quant_cfg,

   llm_config=llm_cfg,

   device="gpu",

   )

   qbcompiler.configs

   Definition compile_config.py:1
3. Automatically applied partial configuration overrides:
   from qbcompiler import mxq_compile

   mxq_compile(

   model="path/to/model.onnx",

   calib_data_path="path/to/calib",

   quantization_method=1, # per channel quantization

   quantization_mode=1, # max percentile quantization

   percentile=0.999, # percentile value for max percentile quantization

   quantization_output=0, # per layer quantization for the output layer

   device="gpu",

   )
   Please refer to the mxq_compile function and the quantization configuration section for the meaning of the quantization-related numeric values.

Compiling models with custom inputs (ONNX/Torch/TensorFlow)

Provide NumPy inputs whenever the model omits shape information so that qbcompiler can infer unknown dimensions and data formats.

from qbcompiler import mxq_compile

import numpy as np

example_input = {

"input_node_name_1": np.random.randn(1, 3, 224, 224).astype(np.float32),

"input_node_name_2": np.random.randn(1, 8, 224, 224).astype(np.float32),

"input_node_name_3": np.random.randn(1, 4, 56, 56).astype(np.float32),

}

in_dformats = {

"input_node_name_1": "NCHW",

"input_node_name_2": "NCHW",

"input_node_name_3": "NCHW",

}

onnx_model_path = "path/to/your/model.onnx"

mxq_compile(

model=onnx_model_path,

feed_dict=example_input,

in_dformats=in_dformats,

backend="onnx",

compile_config="path/to/config.json",

)

Definition at line 128 of file frontend.py.

◆ mblt_compile()

qbcompiler.frontend.mblt_compile	(	str | Any	model,
		str	mblt_save_path,
			backend = "onnx",
			device = "cpu",
			feed_dict = None,
			dynamic_axes = None,
			in_dformats = None,
			yolo_decode_include = False,
			cpu_offload = False,
			use_custom_mask = False,
			exclude_first_subgraph = False,
		**	kwargs )

Export a model to the Mobilint .mblt format without producing an MXQ package.

Parameters

model	string or model instance. Source model or path to compile.
mblt_save_path	string. Output path for the .mblt artifact.
backend	string. Framework identifier ("onnx", "tf", "tflite", "torchscript", or "torch"). Defaults to "onnx".
device	string. Compilation device ("cpu" or "gpu"). Defaults to "cpu".
feed_dict	dict. Example inputs used for shape inference.
dynamic_axes	dict. Declares dynamic axes per input name.
in_dformats	dict. Input dataformat metadata.
yolo_decode_include	bool. Runs YOLO decode on NPU when True.
cpu_offload	bool. Enables CPU offloading for unsupported groups.
use_custom_mask	bool. For non-LLM models that include a mask, use a custom mask provided as a separate input instead of the causal mask. For LLMs that incorporate RoPE, setting LLMConfig.dynamic_rope to True not only enables the use of dynamic RoPE provided via an additional input, but also activates the custom mask.
exclude_first_subgraph	bool. Applies only when CPU offloading is enabled: exclude the first subgraph from the final graph if it is unsupported.
kwargs	dict. Additional arguments forwarded to the compiler.

Returns

None.

Definition at line 424 of file frontend.py.

◆ run_mblt_model()

qbcompiler.frontend.run_mblt_model	(	str	path_to_mblt,
		bool	save_all_outputs = True,
		Optional[str]	inference_output_path = None,
		Optional[int]	target_subgraph = None )

Definition at line 483 of file frontend.py.

◆ get_yaml()

qbcompiler.calibration.make_calib_data.get_yaml

(

str

yaml_path

)

Definition at line 29 of file make_calib_data.py.

◆ make_calib_man()

qbcompiler.calibration.make_calib_data.make_calib_man	(		pre_ftn,
		str	data_dir,
		str	save_dir,
		str	save_name,
		str	anno_json = None,
		str	file_format = "%012d.jpg",
		int	max_size = -1,
		bool	remove_npy = False,
		int	seed = 2023,
		bool	save_calib_msg = False,
		str	msg_path = None )

From images and a user-provided preprocessing function, generate calibration NumPy files and a manifest.

Parameters

pre_ftn	Callable. Pre-processing function that accepts an image path and returns a NumPy array.
data_dir	string. Directory containing the raw calibration images.
save_dir	string. Directory in which to store the generated NumPy files and metadata text file.
save_name	string. Basename for the saved assets. NumPy files are written to {save_dir}/{save_name}_npy and the manifest to {save_dir}/{save_name}.txt. Defaults to the basename of data_dir when omitted.
anno_json	string. Optional COCO-style annotation file. When provided, samples are randomly selected while maintaining class balance.
file_format	string. Filename format that uses image_idx (for example "%012d.jpg").
max_size	int. Maximum number of calibration samples. A value of -1 disables the limit.
remove_npy	bool. Remove existing NumPy outputs before generating new data.
seed	int. Random seed applied to sampling and class-balanced selection. Defaults to 2023.
save_calib_msg	bool. Persist the calibration metadata as an MSGpack file in addition to the manifest.
msg_path	string. Explicit MSGpack output path. When omitted, the path is auto-generated by dataset name and sample count.

Returns

string. Path to the generated text file that lists the preprocessed NumPy samples.

Note

Calibration samples are written as float32 NumPy arrays derived from the pre_ftn output. When max_size is positive and the dataset is larger, a random subset is used. COCO annotations override this sampling to balance categories.

Definition at line 40 of file make_calib_data.py.

◆ make_calib()

str qbcompiler.calibration.make_calib_data.make_calib	(	Union[str, dict]	args_pre,
		str	data_dir,
		str	save_dir,
		str	save_name = None,
		str	anno_json = None,
		str	file_format = "%012d.jpg",
		int	max_size = -1,
		bool	remove_npy = False,
		int	seed = 2023,
		bool	save_calib_msg = False,
		str	msg_path = None )

Create calibration NumPy files and a manifest using a YAML or dict preprocessing configuration.

Parameters

args_pre	string or dict. Path to a YAML file or an in-memory dictionary describing the preprocessing pipeline. See the preproc_builder class for all supported operators and parameters.
data_dir	string. Directory of calibration images.
save_dir	string. Directory where the generated NumPy files and manifest text file are stored.
save_name	string. Optional basename for outputs. Defaults to the basename of data_dir.
anno_json	string. Optional COCO-format annotation file used to sample images with class balance.
file_format	string. Filename template built from image_idx (defaults to "%012d.jpg").
max_size	int. Maximum number of calibration samples to generate; -1 keeps all available items.
remove_npy	bool. Remove existing NumPy outputs before running preprocessing.
seed	int. Random seed used for sampling. Defaults to 2023.
save_calib_msg	bool. Save calibration metadata as MSGpack alongside NumPy and text outputs.
msg_path	string. Explicit MSGpack output path. Auto-generated from dataset name and sample count when omitted.

Returns

string. Path to the manifest text file that lists the generated NumPy samples.

Note

The preprocessing pipeline is constructed through preproc_builder and executed via make_calib_man. Use the YAML schema to combine primitives such as GetImage, Resize, Normalize, Pad, CenterCrop, and SetOrder in a Pre-Order list.

Definition at line 139 of file make_calib_data.py.

◆ make_calib_llm()

List[str] qbcompiler.calibration.make_calib_data.make_calib_llm	(	Union[str, dict]	args_pre,
		str	dataset_name,
		Union[List[str], str]	subset_list,
		str	text_field,
		str	split,
		str	save_dir,
		int	max_calib = 512,
		Optional[str]	save_prefix = None )

Generate calibration embeddings for LLM models using Hugging Face datasets.

Args: args_pre: YAML path or preprocessing configuration dictionary. Must set Datatype to "LLM". dataset_name: Name of the Hugging Face dataset to load. subset_list: List of dataset subsets (e.g. language splits) to iterate. split: HF dataset split to use. text_field: Key containing text in dataset entries. save_dir: Root directory where calibration samples are stored. max_calib: Maximum number of calibration samples per subset. save_prefix: Override prefix used in output directory naming. If None, derives from tokenizer directory name when available.

Returns: List of paths to generated calibration txt files, one per subset.

Definition at line 200 of file make_calib_data.py.

◆ preprocess_fnc()

qbcompiler.calibration.preprocess.preprocess_fnc	(		fnc,
			Datatype = "Image" )

Definition at line 28 of file preprocess.py.

Variable Documentation

◆ DTYPE_GETDATA_MAP

dict qbcompiler.calibration.preprocess.DTYPE_GETDATA_MAP = {"Image": "GetImage", "Npy": "GetNpy", "LLM": "GetText"}

Definition at line 24 of file preprocess.py.

---

Generated by  1.14.0