Python module
max.graph.quantization
Defines quantization encodings and configuration types for MAX graph weights.
Quantization encodings
QuantizationEncoding | Quantization encodings supported by MAX Graph. |
|---|
Configuration
BlockParameters | Parameters describing the structure of a quantization block. |
|---|---|
QuantizationConfig | Configuration for specifying quantization parameters that affect inference. |
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!