icemelon9 commented on a change in pull request #5031: [Strategy] Support for Int8 schedules - CUDA/x86 URL: https://github.com/apache/incubator-tvm/pull/5031#discussion_r391211016
########## File path: topi/python/topi/cuda/conv2d_int8.py ########## @@ -23,10 +24,22 @@ from .injective import schedule_injective_from_existing from .tensor_intrin import dp4a from ..nn.pad import pad +from ..nn.conv2d import unpack_NCHWc_to_nchw from ..nn.util import get_pad_tuple from ..util import get_const_tuple, traverse_inline +def conv2d_nchw_int8(data, kernel, strides, padding, dilation, out_dtype='int32'): Review comment: add a function doc ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
