low-precision topic
List
low-precision repositories
neural-compressor
2.2k
Stars
254
Forks
24
Watchers
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
QPyTorch
254
Stars
70
Forks
Watchers
Low Precision Arithmetic Simulation in PyTorch
ShiftCNN
55
Stars
17
Forks
Watchers
A script to convert floating-point CNN models into generalized low-precision ShiftCNN representation
quantized-yolov5
27
Stars
7
Forks
Watchers
Low Precision(quantized) Yolov5