Python class
ScaleGranularity
ScaleGranularity
class max.nn.ScaleGranularity(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)
Bases: Enum
Specifies the granularity of the quantization scale factor.
Determines whether a scale factor applies per-tensor, per-row (often for weights), per-column, or per-block within a tensor.
BLOCK
BLOCK = 'block'
Per-block scaling.
COLWISE
COLWISE = 'colwise'
Per-column scaling.
ROWWISE
ROWWISE = 'rowwise'
Per-row scaling.
TENSOR
TENSOR = 'tensor'
Per-tensor scaling.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!