Dequantization Fusion
Description
Quantized k and v can be passed to reduce the graphics memory usage. Because the input q is not quantized, the process is also called fake-quantization.
How to Enable
Set quantType to TYPE_DEQUANT_FUSION.
When the preceding parameter is enabled, the hasQuantOffset parameter can be used to specify whether the input quantized KV requires the corresponding offset.
Constraints
Not supported by the
Parent topic: Functions