MCPcopy
hub / github.com/OpenPPL/ppq / custimize_quant_func.py

File custimize_quant_func.py

ppq/samples/custimize_quant_func.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1# This Example shows you how to replace quantization function with your own quant delegator.
2
3from typing import Iterable
4

Callers

nothing calls this directly

Calls 8

quantize_torch_modelFunction · 0.90
TorchExecutorClass · 0.85
toMethod · 0.80
pplcuda_settingMethod · 0.80
register_quantize_delegateMethod · 0.80
remove_quantize_delegateMethod · 0.80
load_calibration_datasetFunction · 0.70
forwardMethod · 0.45

Tested by

no test coverage detected