For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python class

WeightData

WeightData

class max.graph.weights.WeightData(data, name, dtype, shape, quantization_encoding=None)

source

Bases: DLPackArray

Container for weight tensor data with metadata.

WeightData encapsulates a weight tensor along with its metadata, providing utilities for type conversion and format compatibility. It supports the DLPack protocol for efficient tensor sharing between frameworks.

Parameters:

• data (DLPackArray)
• name (str)
• dtype (DType)
• shape (Shape)
• quantization_encoding (QuantizationEncoding | None)

astype()

astype(dtype)

source

Convert the weight data to a different dtype.

This method performs actual data conversion of the underlying tensor data. Special handling is provided for bfloat16 conversions using PyTorch when available.

During cross-compilation (warm-cache) scenarios there is no device to run the conversion on, so the result holds an uninitialized buffer of the target dtype. The values are never read in that mode, and dtype still describes data, which consumers that read the DLPack payload rather than this metadata rely on.

import numpy as np
from max.dtype import DType
from max.graph.weights import WeightData

weight_data = WeightData.from_numpy(
    np.ones((4, 4), dtype=np.float32), "model.layer.weight"
)
fp16_data = weight_data.astype(DType.float16)

Parameters:

dtype (DType) – Target data type for conversion.

Returns:

A new WeightData instance with the converted data.

Return type:

WeightData

data

data: DLPackArray

source

The weight tensor as a DLPack array.

dtype

dtype: DType

source

Data type of the tensor (for example, DType.float32, DType.uint8).

from_numpy()

classmethod from_numpy(arr, name)

source

Create WeightData from a numpy array.

Parameters:

• arr (ndarray[tuple[Any, ...], dtype[Any]]) – Numpy array containing the weight data.
• name (str) – Name to assign to this weight.

Returns:

A new WeightData instance with dtype and shape inferred from the numpy array.

Return type:

WeightData

name

name: str

source

Hierarchical name of the weight (for example, model.layers.0.weight).

quantization_encoding

quantization_encoding: QuantizationEncoding | None = None

source

Optional quantization scheme applied to the weight.

shape

shape: Shape

source

Shape of the tensor as a Shape object.

to_buffer()

to_buffer()

source

Mutates the data into a Buffer.

Return type:

Buffer