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 506a0bbc3f [Relax][PyTorch] Add decomposed operator support for 
AdaptiveAvgPool (#18437)
     add e5fb395c57 [Relax][PyTorch] Add decomposed operator support for 
MaxPool (#18446)
     add 0754ad82d6 [FRONTEND][ONNX] Fix operator Transpose: TVMError: 
PermuteDims expects the number of input axes to equal the ndim of the input 
tensor (#18435)
     add ce0ac662fe [Relax][PyTorch] Add lower bound support for range 
constraints (#18447)
     add 2523ee106f [CI] Update pre-commit configuration (#18448)
     add 1134778847 [DOCS] Remove prebuilt package references and disable Colab 
button at tutorials (#18436)
     add 6c7ed243e5 [DOCS] Update the merge setting (#18451)
     add f8471f820a [Relax][PyTorch] Add decomposed operator support for Pad 
(#18449)
     add b6ac0721a0 [DataType] Update to use explicit Bool Type Aligning with 
DLPack (#18453)

No new revisions were added by this update.

Summary of changes:
 .asf.yaml                                          |  33 +-
 .pre-commit-config.yaml                            |  10 +-
 3rdparty/tvm-ffi                                   |   2 +-
 README.md                                          |  10 +-
 docs/conf.py                                       |  16 +-
 docs/install/index.rst                             |  10 +-
 include/tvm/relax/transform.h                      |  19 +-
 include/tvm/runtime/data_type.h                    |  11 +-
 include/tvm/tir/op.h                               |   6 +-
 python/tvm/relax/frontend/onnx/onnx_frontend.py    |  29 +-
 .../frontend/torch/base_fx_graph_translator.py     |  96 +++++-
 .../frontend/torch/exported_program_translator.py  |  10 +-
 python/tvm/script/parser/tir/operation.py          |   2 +
 python/tvm/tir/ir_builder.py                       |   2 +-
 src/arith/const_fold.h                             |  26 +-
 src/arith/const_int_bound.cc                       |   5 +-
 src/ir/expr.cc                                     |   7 +-
 src/relax/transform/adjust_matmul_order.cc         |  32 +-
 src/relax/transform/static_plan_block_memory.cc    |  38 ++-
 src/relax/transform/utils.h                        |   2 +-
 src/runtime/vm/builtin.cc                          |   2 +-
 src/target/llvm/codegen_llvm.cc                    |   7 +-
 src/target/llvm/codegen_llvm.h                     |   1 +
 src/target/source/codegen_opencl.cc                |   6 +
 src/target/source/codegen_source_base.cc           |   5 +
 src/target/spirv/codegen_spirv.cc                  |   4 +-
 src/target/spirv/ir_builder.cc                     |  61 ++--
 src/tir/ir/expr.cc                                 |   2 +-
 src/tir/ir/stmt.cc                                 |   5 +-
 src/tir/op/op.cc                                   |  55 ++--
 src/tir/transforms/arg_binder.cc                   |   2 +-
 src/tir/transforms/inject_ptx_ldg32.cc             |   2 +-
 src/tir/transforms/lower_tvm_builtin.cc            |   4 +-
 tests/cpp/tir_scalable_datatype.cc                 |   4 +-
 tests/python/arith/test_arith_rewrite_simplify.py  |  22 +-
 .../relax/test_frontend_from_exported_program.py   | 355 +++++++++++++++++----
 tests/python/relax/test_frontend_onnx.py           |  68 ++++
 tests/python/relax/test_op_nn.py                   |   2 -
 .../test_transform_static_plan_block_memory.py     |  12 +
 tests/python/tir-base/test_tir_constructor.py      |  12 +-
 tests/python/tir-base/test_tir_nodes.py            |   2 +-
 tests/python/tir-base/test_tir_ops.py              |  14 +-
 .../tvmscript/test_tvmscript_ir_builder_tir.py     |   2 +-
 .../python/tvmscript/test_tvmscript_printer_tir.py |   4 +-
 44 files changed, 761 insertions(+), 258 deletions(-)

Reply via email to