bitorch_engine.layers.qlinear.nbit.cuda.mpq_layer

Classes

MPQLinearCuda(*args, **kwargs)	Represents a CUDA-compatible implementation of the mixed precision quantized (MPQ) linear layer, inheriting from MPQLinearBase.
MPQLinearCudaFunction(*args, **kwargs)	A custom autograd function for mixed-precision quantized (MPQ) linear operations on CUDA.