This is an automated email from the ASF dual-hosted git repository.
jcf94 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from e934b7e [Doc] Fix Relay pattern rewrite (#8425)
add 0fa4396 [CUDA] dense_tensorcore/batch_matmul_tensorcore support
int8/int4 (#8402)
No new revisions were added by this update.
Summary of changes:
python/tvm/relay/op/strategy/cuda.py | 15 ++-
python/tvm/topi/cuda/batch_matmul_tensorcore.py | 83 ++++++-------
python/tvm/topi/cuda/dense_tensorcore.py | 81 +++++++------
python/tvm/topi/cuda/tensorcore_alter_op.py | 129 +++++++++++----------
python/tvm/topi/testing/__init__.py | 1 +
.../tvm/topi/testing/{batch_matmul.py => dense.py} | 31 ++---
.../python/relay/test_pass_legalize_tensorcore.py | 68 +++++++----
.../python/test_topi_batch_matmul_tensorcore.py | 67 ++++++++---
.../topi/python/test_topi_dense_tensorcore.py | 96 ++++++++++++---
9 files changed, 356 insertions(+), 215 deletions(-)
copy python/tvm/topi/testing/{batch_matmul.py => dense.py} (68%)
