Tim Dettmers c059bd2848 Added additional blocksizes: {64, 128, 256}.		2022-11-20 14:18:15 -08:00
..
common.cpp	Fixed 2^31 max size issue for cpu blockwise quant.	2022-09-11 11:55:09 -07:00
common.h	Fixed 2^31 max size issue for cpu blockwise quant.	2022-09-11 11:55:09 -07:00
cpu_ops.cpp	Fixed cpu blockwise quantization for small input tensors.	2022-09-13 10:37:53 -07:00
cpu_ops.h	Fixed 2^31 max size issue for cpu blockwise quant.	2022-09-11 11:55:09 -07:00
kernels.cu	Added additional blocksizes: {64, 128, 256}.	2022-11-20 14:18:15 -08:00
kernels.cuh	Fixed bug in cpu quant; faster GPU dequant.	2022-11-07 18:06:18 -08:00
ops.cu	Added additional blocksizes: {64, 128, 256}.	2022-11-20 14:18:15 -08:00
ops.cuh	Added blocksizes 2048, 1024, and 512 to blockwise quant.	2022-11-06 16:27:48 -08:00
pythonInterface.c	Added blocksizes 2048, 1024, and 512 to blockwise quant.	2022-11-06 16:27:48 -08:00