MCPcopy Create free account
hub / github.com/ModelTC/LightX2V / quant_utils.py

File quant_utils.py

lightx2v/utils/quant_utils.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1import torch
2from loguru import logger
3
4

Callers

nothing calls this directly

Calls 9

IntegerQuantizerClass · 0.85
FloatQuantizerClass · 0.85
quant_fp8_vllmFunction · 0.85
dequant_fp8_vllmFunction · 0.85
cudaMethod · 0.80
fake_quant_tensorMethod · 0.80
infoMethod · 0.80
real_quant_tensorMethod · 0.80
toMethod · 0.45

Tested by

no test coverage detected