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 38b85c9f61 [Fix][dlight] add an explicit reduction loop check in
Reduce (#17711)
add be8e43814a [Refactor] Migrate build API to `tvm.compile` (#17718)
add 56bfd72f7b [FFI] Fix dynamic FFI index to ensure compatibility (#17727)
add e973770932 [DataType] BF16 Support (#17670)
No new revisions were added by this update.
Summary of changes:
apps/android_rpc/tests/android_rpc_test.py | 2 +-
apps/ios_rpc/tests/ios_rpc_test.py | 2 +-
docs/deep_dive/tensor_ir/tutorials/tir_creation.py | 2 +-
.../tensor_ir/tutorials/tir_transformation.py | 2 +-
docs/get_started/tutorials/ir_module.py | 4 +-
docs/get_started/tutorials/quick_start.py | 2 +-
docs/how_to/tutorials/cross_compilation_and_rpc.py | 4 +-
docs/how_to/tutorials/customize_opt.py | 2 +-
docs/how_to/tutorials/e2e_opt_model.py | 2 +-
docs/reference/api/python/driver.rst | 2 +-
include/tvm/runtime/data_type.h | 2 +
include/tvm/runtime/object.h | 9 +-
include/tvm/runtime/profiling.h | 2 +-
include/tvm/script/ir_builder/tir/ir.h | 2 +
python/tvm/_ffi/runtime_ctypes.py | 1 +
python/tvm/contrib/msc/core/runtime/runner.py | 4 +-
.../contrib/msc/framework/tvm/runtime/runner.py | 8 +-
python/tvm/dlight/benchmark/bench.py | 2 +-
python/tvm/exec/gpu_memory_bandwidth.py | 4 +-
python/tvm/ir/instrument.py | 2 +-
.../tvm/meta_schedule/testing/validate_database.py | 2 +-
python/tvm/relax/frontend/nn/extern.py | 2 +-
python/tvm/relax/pipeline.py | 4 +-
python/tvm/relax/training/trainer.py | 2 +-
.../transform/tuning_api/default_functions.py | 2 +-
python/tvm/relax/vm_build.py | 2 +-
python/tvm/runtime/profiling/__init__.py | 2 +-
python/tvm/runtime/relax_vm.py | 6 +-
python/tvm/script/ir_builder/tir/ir.py | 4 +-
python/tvm/testing/utils.py | 2 +-
python/tvm/topi/sort.py | 2 +-
.../postproc/disallow_async_strided_mem_copy.cc | 10 +-
src/relax/op/nn/nn.cc | 3 +-
src/relax/op/op_common.h | 3 +-
src/script/ir_builder/tir/ir.cc | 2 +
src/target/source/codegen_c_host.cc | 14 +-
src/target/source/codegen_cuda.cc | 2 +-
src/target/source/intrin_rule_cuda.cc | 8 +-
src/tir/op/op.cc | 2 +-
src/tir/transforms/unsupported_dtype_legalize.cc | 48 ++-
.../test_minimal_target_codegen_llvm.py | 2 +-
tests/python/codegen/test_gpu_codegen_allreduce.py | 6 +-
tests/python/codegen/test_inject_ptx_ldg32.py | 2 +-
tests/python/codegen/test_target_codegen.py | 8 +-
.../python/codegen/test_target_codegen_aarch64.py | 40 +--
tests/python/codegen/test_target_codegen_arm.py | 8 +-
tests/python/codegen/test_target_codegen_blob.py | 4 +-
tests/python/codegen/test_target_codegen_bool.py | 2 +-
tests/python/codegen/test_target_codegen_c_host.py | 12 +-
.../codegen/test_target_codegen_cross_llvm.py | 4 +-
tests/python/codegen/test_target_codegen_cuda.py | 57 ++--
.../python/codegen/test_target_codegen_cuda_fp4.py | 8 +-
.../python/codegen/test_target_codegen_cuda_fp8.py | 24 +-
tests/python/codegen/test_target_codegen_device.py | 4 +-
tests/python/codegen/test_target_codegen_extern.py | 6 +-
.../codegen/test_target_codegen_gpu_common.py | 2 +-
.../python/codegen/test_target_codegen_hexagon.py | 6 +-
tests/python/codegen/test_target_codegen_llvm.py | 93 +++---
tests/python/codegen/test_target_codegen_metal.py | 14 +-
tests/python/codegen/test_target_codegen_opencl.py | 23 +-
tests/python/codegen/test_target_codegen_riscv.py | 5 +-
tests/python/codegen/test_target_codegen_rocm.py | 8 +-
tests/python/codegen/test_target_codegen_vulkan.py | 18 +-
tests/python/codegen/test_target_codegen_x86.py | 7 +-
tests/python/contrib/test_cblas.py | 8 +-
tests/python/contrib/test_dlpack.py | 2 +-
.../python/contrib/test_hexagon/infrastructure.py | 2 +-
.../test_hexagon/test_2d_physical_buffers.py | 4 +-
.../test_hexagon/test_async_dma_pipeline.py | 2 +-
.../test_hexagon/test_benchmark_elemwise_add.py | 2 +-
.../test_hexagon/test_benchmark_maxpool2d.py | 2 +-
.../contrib/test_hexagon/test_dma_builtin.py | 2 +-
.../contrib/test_hexagon/test_memory_alloc.py | 2 +-
.../contrib/test_hexagon/test_meta_schedule.py | 2 +-
.../contrib/test_hexagon/test_parallel_hvx.py | 2 +-
.../test_hexagon/test_parallel_hvx_load_vtcm.py | 4 +-
.../contrib/test_hexagon/test_parallel_scalar.py | 2 +-
.../test_relax_2d_buffer_allocation.py | 2 +-
.../contrib/test_hexagon/test_relax_integration.py | 8 +-
tests/python/contrib/test_hexagon/test_sigmoid.py | 2 +-
.../test_hexagon/test_software_pipeline_async.py | 2 +-
tests/python/contrib/test_hexagon/test_take.py | 2 +-
.../contrib/test_hexagon/test_thread_pool.py | 4 +-
tests/python/contrib/test_hexagon/test_vtcm.py | 8 +-
.../contrib/test_hexagon/test_vtcm_bandwidth.py | 2 +-
tests/python/contrib/test_hipblas.py | 4 +-
tests/python/contrib/test_mps.py | 4 +-
tests/python/contrib/test_msc/test_plugin.py | 2 +-
.../contrib/test_msc/test_translate_relax.py | 2 +-
.../contrib/test_msc/test_translate_tensorrt.py | 2 +-
tests/python/contrib/test_random.py | 6 +-
tests/python/contrib/test_rocblas.py | 4 +-
tests/python/contrib/test_sort.py | 4 +-
.../python/contrib/test_tir_triton_integration.py | 2 +-
tests/python/disco/test_callback.py | 2 +-
tests/python/disco/test_ccl.py | 4 +-
tests/python/disco/test_loader.py | 2 +-
tests/python/disco/test_session.py | 4 +-
tests/python/ir/test_datatype_nv_fp8.py | 2 +-
tests/python/ir/test_pass_instrument.py | 2 +-
.../meta_schedule/test_meta_schedule_tune_tir.py | 2 +-
tests/python/nightly/test_nnapi/infrastructure.py | 2 +-
tests/python/nightly/test_nnapi/test_network.py | 2 +-
tests/python/nightly/test_nnapi/test_ops.py | 2 +-
tests/python/relax/backend/clml/utils.py | 4 +-
.../test_runtime_builtin_kv_cache_transfer.py | 2 +-
.../relax/test_backend_dispatch_sort_scan.py | 2 +-
tests/python/relax/test_codegen_coreml.py | 4 +-
tests/python/relax/test_codegen_cublas.py | 2 +-
tests/python/relax/test_codegen_cudnn.py | 2 +-
tests/python/relax/test_codegen_cutlass.py | 18 +-
tests/python/relax/test_codegen_dnnl.py | 2 +-
tests/python/relax/test_codegen_hipblas.py | 2 +-
tests/python/relax/test_codegen_tensorrt.py | 2 +-
tests/python/relax/test_codegen_tir_cutlass.py | 12 +-
tests/python/relax/test_contrib_vllm.py | 2 +-
tests/python/relax/test_dataflow_inplace.py | 4 +-
tests/python/relax/test_dataflow_pattern.py | 4 +-
tests/python/relax/test_e2e_op_dynamic.py | 2 +-
.../python/relax/test_frontend_nn_extern_module.py | 4 +-
tests/python/relax/test_frontend_nn_op.py | 8 +-
tests/python/relax/test_frontend_onnx.py | 2 +-
tests/python/relax/test_frontend_stablehlo.py | 4 +-
tests/python/relax/test_op_gradient_numeric.py | 4 +-
tests/python/relax/test_op_inspect.py | 18 +-
tests/python/relax/test_op_take.py | 10 +-
tests/python/relax/test_op_view.py | 10 +-
tests/python/relax/test_pipeline.py | 4 +-
...runtime_builtin_paged_attention_kv_cache_cpu.py | 2 +-
..._builtin_paged_attention_kv_cache_flashinfer.py | 2 +-
...ltin_paged_attention_kv_cache_mla_flashinfer.py | 2 +-
...ime_builtin_paged_attention_kv_cache_mla_tir.py | 2 +-
...runtime_builtin_paged_attention_kv_cache_tir.py | 2 +-
.../python/relax/test_runtime_builtin_rnn_state.py | 2 +-
tests/python/relax/test_tir_call_source_kernel.py | 2 +-
.../relax/test_training_optimizer_numeric.py | 2 +-
.../python/relax/test_training_trainer_numeric.py | 8 +-
tests/python/relax/test_transform_bind_params.py | 4 +-
tests/python/relax/test_transform_codegen_pass.py | 6 +-
.../python/relax/test_transform_few_shot_tuning.py | 4 +-
.../test_transform_fold_batch_norm_to_conv2d.py | 4 +-
.../relax/test_transform_gradient_numeric.py | 2 +-
.../relax/test_transform_lazy_transform_params.py | 2 +-
.../relax/test_vm_alloc_storage_with_scope.py | 6 +-
tests/python/relax/test_vm_builtin.py | 4 +-
tests/python/relax/test_vm_callback_function.py | 6 +-
tests/python/relax/test_vm_cuda_graph.py | 2 +-
tests/python/relax/test_vm_execbuilder.py | 2 +-
tests/python/relax/test_vm_instrument.py | 4 +-
tests/python/relax/test_vm_multi_device.py | 2 +-
tests/python/relax/test_vm_profiler.py | 4 +-
.../python/runtime/test_evaluator_with_preproc.py | 10 +-
tests/python/runtime/test_runtime_dlpack.py | 2 +-
tests/python/runtime/test_runtime_extension.py | 2 +-
tests/python/runtime/test_runtime_measure.py | 2 +-
tests/python/runtime/test_runtime_module_export.py | 4 +-
tests/python/runtime/test_runtime_module_load.py | 25 +-
.../python/runtime/test_runtime_module_property.py | 2 +-
tests/python/runtime/test_runtime_rpc.py | 10 +-
tests/python/runtime/test_runtime_trace.py | 14 +-
tests/python/target/test_arm_target.py | 8 +-
tests/python/target/test_target_target.py | 2 +-
tests/python/te/test_te_create_primfunc.py | 4 +-
tests/python/tir-base/test_tir_base.py | 2 +-
tests/python/tir-base/test_tir_imm_values.py | 48 +--
tests/python/tir-base/test_tir_intrin.py | 10 +-
tests/python/tir-base/test_tir_ptx_cp_async.py | 6 +-
tests/python/tir-base/test_tir_ptx_ldmatrix.py | 2 +-
tests/python/tir-base/test_tir_ptx_mma.py | 40 ++-
tests/python/tir-base/test_tir_ptx_mma_sp.py | 4 +-
.../python/tir-base/test_tir_te_extern_primfunc.py | 4 +-
tests/python/tir-base/test_tir_texture_scope.py | 2 +-
.../test_tir_schedule_decompose_padding.py | 4 +-
.../test_tir_schedule_rolling_buffer.py | 4 +-
..._tir_schedule_tensorize_ldmatrix_mma_numeric.py | 2 +-
.../test_tir_schedule_tensorize_mfma_numeric.py | 2 +-
.../test_tir_transform_bf16_legalize.py | 364 ++++++++++++++++-----
.../test_tir_transform_inject_ptx_async_copy.py | 10 +-
.../test_tir_transform_inject_software_pipeline.py | 2 +-
.../test_tir_transform_lower_intrin.py | 2 +-
.../test_tir_transform_lower_tvm_builtin.py | 4 +-
.../test_tir_transform_make_packed_api.py | 8 +-
.../tir-transform/test_tir_transform_vectorize.py | 6 +-
tests/python/tvmscript/test_tvmscript_ops.py | 8 +-
184 files changed, 869 insertions(+), 619 deletions(-)
