Jzz24

SenseTimeBeijing

Pinned Repositories

AutoAWQ
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Language:Python1.9k 15 429228
lectures
Material for gpu-mode lectures
Language:Jupyter Notebook00
ppl.pmx
Language:Python0 0 00
ppq
Language:Python0 0 00
pytorch_quantization
A pytorch implementation of dorefa quantization
Language:Python112 2 811
ppl.pmx
Language:Python57 3 1014
ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Language:Python1.6k 17 236240
ppq_tools
Language:Python7 1 02

Jzz24's Repositories

Jzz24/pytorch_quantization
A pytorch implementation of dorefa quantization
Language:Python112 2 811
Jzz24/lectures
Material for gpu-mode lectures
Language:Jupyter Notebook00
Jzz24/ppl.pmx
Language:Python0 0 00
Jzz24/ppq
Language:Python0 0 00