This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from e973770932 [DataType] BF16 Support (#17670)
add 63b54c4547 [Relax][PyTorch] Add support for numel, empty_like and
one_hot ops (#17726)
add 2601733f56 [Relax] ingest Tensor.contiguous from torch export (#17728)
add d0de9067bc [Relax] Allow ingesting vector_norm from torch.export
(#17722)
add cf6e61b285 [Relax] Allow ingesting Upsample module from torch.export
either using Size or Scale Factor argument (#17721)
add 6e8c367fd7 [Relax] Add torch exported program ingestion capability for
Tensor.detach(), Tensor.copy_, and aten.lift_fresh_copy (#17723)
No new revisions were added by this update.
Summary of changes:
.../frontend/torch/base_fx_graph_translator.py | 52 +++++++
.../frontend/torch/exported_program_translator.py | 48 ++++++-
python/tvm/relax/frontend/torch/fx_translator.py | 20 +++
tests/python/relax/test_from_exported_to_cuda.py | 157 +++++++++++++++++++++
.../relax/test_frontend_from_exported_program.py | 20 +++
tests/python/relax/test_frontend_from_fx.py | 62 ++++++++
6 files changed, 352 insertions(+), 7 deletions(-)
create mode 100644 tests/python/relax/test_from_exported_to_cuda.py
