python/tvm/relay/frontend · 681df4fcd57851b96e6fdc47c1576908c8636bd3 · wenyuanbo / tic

[Strategy] Support for Int8 schedules - CUDA/x86 (#5031) · 681df4fc

* [CUDA] Op strategy changes for Int8 schedules.

* Applying Haichen's suggestions.

* Make 4D output work for task extraction.

* Make x86 work.

* Fix lint.

* Lint fixes.

* Tests, comments, out channel a multiple of 4.

* Topi test.

Co-authored-by: Ubuntu <ubuntu@ip-172-31-38-96.us-west-2.compute.internal>

committed Mar 12, 2020

681df4fc

Name	Last commit	Last update
..
__init__.py		Loading commit data...
caffe2.py		Loading commit data...
common.py		Loading commit data...
coreml.py		Loading commit data...
darknet.py		Loading commit data...
keras.py		Loading commit data...
mxnet.py		Loading commit data...
mxnet_qnn_op_utils.py		Loading commit data...
nnvm_common.py		Loading commit data...
onnx.py		Loading commit data...
pytorch.py		Loading commit data...
qnn_torch.py		Loading commit data...
tensorflow.py		Loading commit data...
tensorflow_parser.py		Loading commit data...
tflite.py		Loading commit data...