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 c35f868531 [CI] Update images to `20260219-160550-72f51851` (#18800)
add f533d0b3c1 [REFACTOR] Migrate CHECK macros to tvm-ffi ones (#18803)
add 7e2ebc928f [REFACTOR][TEST] Remove unused te imports from test files
(#18804)
add c0828bc8ad [REFACTOR][TEST] Migrate tir-transform tests from TE to
TVMScript (#18805)
No new revisions were added by this update.
Summary of changes:
3rdparty/cutlass_fpA_intB_gemm | 2 +-
3rdparty/nvbench/l2_cache_flush.h | 10 +-
apps/cpp_rpc/main.cc | 2 +-
apps/cpp_rpc/rpc_env.cc | 16 +-
apps/cpp_rpc/rpc_server.cc | 20 +-
apps/cpp_rpc/rpc_tracker_client.h | 14 +-
apps/cpp_rpc/win32_process.cc | 25 +-
apps/hexagon_launcher/launcher_core.cc | 2 +-
apps/hexagon_launcher/launcher_util.cc | 6 +-
include/tvm/arith/analyzer.h | 4 +-
include/tvm/ir/attrs.h | 3 +-
include/tvm/ir/diagnostic.h | 33 +-
include/tvm/ir/env_func.h | 4 +-
include/tvm/ir/expr.h | 2 +-
include/tvm/ir/module.h | 2 +-
include/tvm/ir/name_supply.h | 3 +-
include/tvm/ir/op.h | 4 +-
include/tvm/ir/source_map.h | 2 +-
include/tvm/ir/transform.h | 4 +-
include/tvm/ir/type_functor.h | 4 +-
include/tvm/node/attr_registry_map.h | 6 +-
include/tvm/node/functor.h | 15 +-
include/tvm/node/repr_printer.h | 2 +-
include/tvm/relax/binding_rewrite.h | 2 +-
include/tvm/relax/dataflow_pattern.h | 6 +-
include/tvm/relax/dataflow_pattern_functor.h | 4 +-
include/tvm/relax/distributed/axis_group_graph.h | 11 +-
include/tvm/relax/expr_functor.h | 7 +-
include/tvm/relax/nested_msg.h | 29 +-
include/tvm/relax/struct_info.h | 4 +-
include/tvm/relax/struct_info_functor.h | 4 +-
include/tvm/runtime/data_type.h | 17 +-
include/tvm/runtime/device_api.h | 8 +-
include/tvm/runtime/disco/builtin.h | 2 +-
include/tvm/runtime/disco/session.h | 2 +-
include/tvm/runtime/logging.h | 261 +-----------
include/tvm/runtime/object.h | 2 +-
include/tvm/runtime/tensor.h | 35 +-
include/tvm/runtime/vm/bytecode.h | 9 +-
include/tvm/s_tir/data_layout.h | 4 +-
include/tvm/s_tir/meta_schedule/builder.h | 2 +-
include/tvm/s_tir/meta_schedule/database.h | 15 +-
include/tvm/s_tir/meta_schedule/runner.h | 6 +-
include/tvm/s_tir/sblock_dependence_info.h | 4 +-
include/tvm/s_tir/utils.h | 46 +-
include/tvm/script/ir_builder/base.h | 9 +-
include/tvm/script/printer/ir_docsifier.h | 2 +-
include/tvm/script/printer/ir_docsifier_functor.h | 13 +-
include/tvm/support/random_engine.h | 4 +-
include/tvm/target/target_kind.h | 2 +-
include/tvm/target/virtual_device.h | 6 +-
include/tvm/tir/expr_functor.h | 4 +-
include/tvm/tir/op.h | 4 +-
include/tvm/tir/op_attr_types.h | 2 +-
include/tvm/tir/stmt.h | 2 +-
include/tvm/tir/stmt_functor.h | 2 +-
include/tvm/topi/broadcast.h | 6 +-
include/tvm/topi/detail/broadcast.h | 19 +-
include/tvm/topi/detail/constant_utils.h | 6 +-
include/tvm/topi/detail/extern.h | 4 +-
include/tvm/topi/detail/ravel_unravel.h | 2 +-
include/tvm/topi/detail/strided_slice.h | 8 +-
include/tvm/topi/elemwise.h | 2 +-
include/tvm/topi/nn.h | 39 +-
include/tvm/topi/nn/bnn.h | 10 +-
include/tvm/topi/nn/dense.h | 6 +-
include/tvm/topi/nn/dilate.h | 6 +-
include/tvm/topi/nn/group_norm.h | 6 +-
include/tvm/topi/nn/instance_norm.h | 6 +-
include/tvm/topi/nn/layer_norm.h | 6 +-
include/tvm/topi/nn/local_response_norm.h | 8 +-
include/tvm/topi/nn/pooling.h | 39 +-
include/tvm/topi/nn/rms_norm.h | 4 +-
include/tvm/topi/nn/softmax.h | 4 +-
include/tvm/topi/reduction.h | 12 +-
include/tvm/topi/transform.h | 176 ++++----
src/arith/analyzer.cc | 6 +-
src/arith/bound_deducer.cc | 2 +-
src/arith/canonical_simplify.cc | 38 +-
src/arith/conjunctive_normal_form.cc | 2 +-
src/arith/const_fold.h | 26 +-
src/arith/const_int_bound.cc | 20 +-
src/arith/detect_common_subexpr.cc | 4 +-
src/arith/domain_touched.cc | 3 +-
src/arith/int_constraints.cc | 16 +-
src/arith/int_set.cc | 34 +-
src/arith/ir_mutator_with_analyzer.cc | 2 +-
src/arith/ir_visitor_with_analyzer.cc | 2 +-
src/arith/iter_affine_map.cc | 46 +-
src/arith/modular_set.cc | 6 +-
src/arith/narrow_predicate_expression.cc | 4 +-
src/arith/pattern_match.h | 8 +-
src/arith/presburger_set.cc | 11 +-
src/arith/presburger_set.h | 4 +-
src/arith/rewrite_simplify.cc | 21 +-
src/arith/rewrite_simplify.h | 3 +-
src/arith/solve_linear_equation.cc | 7 +-
src/arith/solve_linear_inequality.cc | 52 +--
src/arith/transitive_comparison_analyzer.cc | 27 +-
src/arith/unwrap_vector_expr.cc | 2 +-
src/contrib/msc/core/codegen/base_codegen.h | 10 +-
src/contrib/msc/core/codegen/code_stack.cc | 36 +-
src/contrib/msc/core/codegen/codegen_json.h | 4 +-
src/contrib/msc/core/codegen/cpp_codegen.h | 2 +-
src/contrib/msc/core/ir/graph.cc | 34 +-
src/contrib/msc/core/ir/graph.h | 17 +-
src/contrib/msc/core/ir/graph_builder.cc | 68 +--
src/contrib/msc/core/ir/graph_builder.h | 2 +-
src/contrib/msc/core/ir/plugin.h | 14 +-
src/contrib/msc/core/printer/cpp_printer.cc | 20 +-
src/contrib/msc/core/printer/cpp_printer.h | 8 +-
src/contrib/msc/core/printer/msc_base_printer.cc | 4 +-
src/contrib/msc/core/printer/msc_base_printer.h | 74 +++-
src/contrib/msc/core/printer/print_utils.cc | 2 +-
src/contrib/msc/core/printer/prototxt_printer.cc | 4 +-
src/contrib/msc/core/printer/python_printer.cc | 9 +-
.../msc/core/transform/bind_named_params.cc | 19 +-
src/contrib/msc/core/transform/bind_shape.cc | 8 +-
src/contrib/msc/core/transform/fuse_tuple.cc | 9 +-
src/contrib/msc/core/transform/inline_params.cc | 13 +-
src/contrib/msc/core/transform/layout_utils.cc | 8 +-
src/contrib/msc/core/transform/set_byoc_attrs.cc | 2 +-
src/contrib/msc/core/transform/set_expr_layout.cc | 10 +-
src/contrib/msc/core/utils.cc | 11 +-
src/contrib/msc/core/utils.h | 2 +-
src/contrib/msc/framework/tensorflow/codegen.cc | 3 +-
.../msc/framework/tensorflow/tf_v1_opcode.cc | 7 +-
src/contrib/msc/framework/tensorrt/codegen.cc | 7 +-
src/contrib/msc/framework/tensorrt/codegen_utils.h | 4 +-
.../msc/framework/tensorrt/tensorrt_opcode.cc | 13 +-
.../msc/framework/tensorrt/transform_tensorrt.cc | 4 +-
src/contrib/msc/framework/torch/codegen.cc | 2 +-
src/contrib/msc/framework/torch/codegen_utils.h | 2 +-
src/contrib/msc/framework/torch/torch_opcode.cc | 15 +-
src/contrib/msc/framework/tvm/codegen.cc | 2 +-
src/contrib/msc/framework/tvm/relax_opcode.cc | 5 +-
src/contrib/msc/plugin/base_codegen.h | 2 +-
src/contrib/msc/plugin/tensorrt_codegen.cc | 3 +-
src/contrib/msc/plugin/torch_codegen.cc | 2 +-
src/contrib/msc/plugin/tvm_codegen.cc | 5 +-
src/ir/apply_pass_to_function.cc | 2 +-
src/ir/diagnostic.cc | 41 +-
src/ir/env_func.cc | 4 +-
src/ir/expr.cc | 90 ++--
src/ir/function.cc | 8 +-
src/ir/global_var_supply.cc | 4 +-
src/ir/instrument.cc | 5 +-
src/ir/module.cc | 26 +-
src/ir/op.cc | 8 +-
src/ir/replace_global_vars.cc | 4 +-
src/ir/source_map.cc | 6 +-
src/ir/transform.cc | 35 +-
src/node/attr_registry.h | 11 +-
src/node/script_printer.cc | 8 +-
src/node/structural_hash.cc | 2 +-
src/relax/analysis/analysis.cc | 2 +-
src/relax/analysis/graph_partitioner.cc | 32 +-
src/relax/analysis/layout_transformation.cc | 23 +-
src/relax/analysis/struct_info_analysis.cc | 12 +-
src/relax/analysis/tir_op_pattern_kind.cc | 8 +-
src/relax/analysis/udchain.cc | 5 +-
src/relax/analysis/well_formed.cc | 8 +-
.../backend/adreno/annotate_custom_storage.cc | 14 +-
.../backend/adreno/fold_vdevice_scope_change.cc | 21 +-
src/relax/backend/contrib/clml/codegen.cc | 16 +-
src/relax/backend/contrib/codegen_c/codegen_c.h | 8 +-
.../backend/contrib/codegen_json/codegen_json.h | 39 +-
src/relax/backend/contrib/cublas/codegen.cc | 10 +-
src/relax/backend/contrib/cudnn/codegen.cc | 12 +-
src/relax/backend/contrib/cutlass/codegen.cc | 29 +-
src/relax/backend/contrib/dnnl/codegen.cc | 8 +-
src/relax/backend/contrib/hipblas/codegen.cc | 8 +-
src/relax/backend/contrib/nnapi/codegen.cc | 20 +-
src/relax/backend/contrib/tensorrt/codegen.cc | 6 +-
src/relax/backend/contrib/utils.cc | 9 +-
src/relax/backend/contrib/utils.h | 2 +-
src/relax/backend/task_extraction.cc | 2 +-
src/relax/backend/vm/codegen_vm.cc | 34 +-
src/relax/backend/vm/codegen_vm_tir.cc | 39 +-
src/relax/backend/vm/exec_builder.cc | 46 +-
src/relax/backend/vm/lower_runtime_builtin.cc | 51 ++-
src/relax/backend/vm/vm_shape_lower.cc | 33 +-
src/relax/distributed/axis_group_graph.cc | 26 +-
src/relax/distributed/global_info.cc | 4 +-
src/relax/distributed/struct_info.cc | 14 +-
.../distributed/transform/legalize_redistribute.cc | 14 +-
src/relax/distributed/transform/lower_distir.cc | 21 +-
.../transform/lower_global_view_to_local_view.cc | 19 +-
.../distributed/transform/propagate_sharding.cc | 29 +-
src/relax/distributed/transform/utils.cc | 4 +-
src/relax/ir/binding_rewrite.cc | 15 +-
src/relax/ir/block_builder.cc | 72 ++--
src/relax/ir/dataflow_block_rewriter.cc | 7 +-
src/relax/ir/dataflow_expr_rewriter.cc | 76 ++--
src/relax/ir/dataflow_matcher.cc | 5 +-
src/relax/ir/dataflow_pattern.cc | 6 +-
src/relax/ir/emit_te.cc | 9 +-
src/relax/ir/expr.cc | 33 +-
src/relax/ir/expr_functor.cc | 81 ++--
src/relax/ir/py_expr_functor.cc | 12 +-
src/relax/ir/struct_info.cc | 38 +-
src/relax/ir/struct_info_functor.cc | 2 +-
src/relax/ir/transform.cc | 18 +-
src/relax/op/ccl/ccl.cc | 3 +-
src/relax/op/distributed/binary.h | 4 +-
src/relax/op/distributed/ccl.cc | 2 +-
src/relax/op/distributed/distributed.cc | 16 +-
src/relax/op/distributed/linear_algebra.cc | 4 +-
src/relax/op/distributed/manipulate.cc | 2 +-
src/relax/op/distributed/nn.cc | 2 +-
src/relax/op/distributed/op.cc | 2 +-
src/relax/op/distributed/statistical.cc | 4 +-
src/relax/op/distributed/unary.h | 2 +-
src/relax/op/distributed/utils.cc | 6 +-
src/relax/op/image/resize.cc | 5 +-
src/relax/op/memory/view.cc | 97 +++--
src/relax/op/nn/convolution.cc | 96 +++--
src/relax/op/nn/nn.cc | 88 ++--
src/relax/op/nn/pooling.cc | 72 ++--
src/relax/op/op.cc | 135 +++---
src/relax/op/op_common.cc | 8 +-
src/relax/op/op_common.h | 48 +--
src/relax/op/tensor/binary.cc | 14 +-
src/relax/op/tensor/create.cc | 6 +-
src/relax/op/tensor/index.cc | 94 +++--
src/relax/op/tensor/inspect.cc | 41 +-
src/relax/op/tensor/linear_algebra.cc | 2 +-
src/relax/op/tensor/manipulate.cc | 215 +++++-----
src/relax/op/tensor/search.cc | 6 +-
src/relax/op/tensor/set.cc | 8 +-
src/relax/op/tensor/sorting.cc | 2 +-
src/relax/op/tensor/statistical.cc | 16 +-
src/relax/op/tensor/ternary.cc | 2 +-
src/relax/op/tensor/unary.cc | 4 +-
src/relax/op/vision/nms.cc | 8 +-
src/relax/training/utils.cc | 22 +-
src/relax/transform/adjust_matmul_order.cc | 14 +-
src/relax/transform/allocate_workspace.cc | 4 +-
src/relax/transform/alter_op_impl.cc | 20 +-
.../transform/attach_attr_layout_free_buffers.cc | 3 +-
src/relax/transform/bind_params.cc | 43 +-
src/relax/transform/bind_symbolic_vars.cc | 30 +-
src/relax/transform/bundle_model_params.cc | 4 +-
src/relax/transform/call_tir_rewrite.cc | 14 +-
src/relax/transform/canonicalize_bindings.cc | 11 +-
src/relax/transform/combine_parallel_matmul.cc | 8 +-
src/relax/transform/convert_layout.cc | 18 +-
src/relax/transform/dataflow_inplace.cc | 2 +-
src/relax/transform/decompose_ops.cc | 14 +-
src/relax/transform/eliminate_common_subexpr.cc | 4 +-
src/relax/transform/expand_matmul_of_sum.cc | 4 +-
src/relax/transform/few_shot_tuning.cc | 15 +-
src/relax/transform/fold_constant.cc | 18 +-
src/relax/transform/fuse_ops.cc | 69 +--
src/relax/transform/fuse_tir.cc | 178 ++++----
src/relax/transform/gradient.cc | 90 ++--
src/relax/transform/gradient_simplifier.cc | 4 +-
src/relax/transform/infer_amp_utils.cc | 6 +-
src/relax/transform/infer_layout_utils.cc | 23 +-
src/relax/transform/inline_functions.cc | 7 +-
src/relax/transform/kill_after_last_use.cc | 6 +-
src/relax/transform/lambda_lift.cc | 24 +-
src/relax/transform/lazy_transform_params.cc | 9 +-
src/relax/transform/lift_transform_params.cc | 46 +-
src/relax/transform/lower_alloc_tensor.cc | 14 +-
src/relax/transform/merge_composite_functions.cc | 10 +-
src/relax/transform/meta_schedule.cc | 8 +-
src/relax/transform/normalize.cc | 8 +-
src/relax/transform/realize_vdevice.cc | 29 +-
src/relax/transform/remove_unused_outputs.cc | 25 +-
src/relax/transform/remove_unused_parameters.cc | 8 +-
.../transform/reorder_permute_dims_after_concat.cc | 19 +-
src/relax/transform/reorder_take_after_matmul.cc | 14 +-
src/relax/transform/rewrite_cuda_graph.cc | 18 +-
src/relax/transform/rewrite_dataflow_reshape.cc | 6 +-
src/relax/transform/run_codegen.cc | 6 +-
.../specialize_primfunc_based_on_callsite.cc | 12 +-
src/relax/transform/split_call_tir_by_pattern.cc | 18 +-
.../transform/split_layout_rewrite_preproc.cc | 37 +-
src/relax/transform/static_plan_block_memory.cc | 89 ++--
src/relax/transform/to_mixed_precision.cc | 18 +-
src/relax/transform/topological_sort.cc | 83 ++--
src/relax/transform/utils.cc | 3 +-
src/relax/transform/utils.h | 22 +-
src/relax/utils.cc | 5 +-
src/runtime/const_loader_module.cc | 26 +-
src/runtime/contrib/amx/amx_config.cc | 20 +-
.../contrib/arm_compute_lib/acl_allocator.cc | 2 +-
src/runtime/contrib/arm_compute_lib/acl_runtime.cc | 34 +-
src/runtime/contrib/arm_compute_lib/acl_utils.cc | 13 +-
src/runtime/contrib/bnns/bnns_json_runtime.cc | 33 +-
src/runtime/contrib/bnns/bnns_wrp.h | 24 +-
src/runtime/contrib/cblas/cblas.cc | 60 +--
src/runtime/contrib/cblas/dnnl_blas.cc | 2 +-
src/runtime/contrib/cblas/gemm_common.h | 60 +--
src/runtime/contrib/cblas/mkl.cc | 50 +--
src/runtime/contrib/clml/clml_memory_planner.cc | 2 +-
src/runtime/contrib/clml/clml_runtime.cc | 108 ++---
src/runtime/contrib/clml/clml_runtime.h | 83 ++--
src/runtime/contrib/clml/clml_utils.cc | 14 +-
src/runtime/contrib/cublas/cublas.cc | 84 ++--
src/runtime/contrib/cublas/cublas_json_runtime.cc | 8 +-
src/runtime/contrib/cublas/cublas_utils.h | 10 +-
.../contrib/cudnn/cudnn_frontend/attention.cc | 10 +-
.../contrib/cudnn/cudnn_frontend/attention.h | 8 +-
src/runtime/contrib/cudnn/cudnn_json_runtime.cc | 16 +-
src/runtime/contrib/cudnn/cudnn_utils.cc | 11 +-
src/runtime/contrib/cudnn/cudnn_utils.h | 8 +-
src/runtime/contrib/cudnn/softmax.cc | 2 +-
src/runtime/contrib/curand/curand.cc | 14 +-
src/runtime/contrib/dnnl/dnnl.cc | 4 +-
src/runtime/contrib/dnnl/dnnl_json_runtime.cc | 44 +-
src/runtime/contrib/dnnl/dnnl_tensor_requisite.h | 57 +--
src/runtime/contrib/hipblas/hipblas.cc | 62 +--
.../contrib/hipblas/hipblas_json_runtime.cc | 8 +-
src/runtime/contrib/hipblas/hipblas_utils.h | 13 +-
src/runtime/contrib/json/json_node.h | 8 +-
src/runtime/contrib/json/json_runtime.h | 30 +-
src/runtime/contrib/miopen/miopen_utils.h | 8 +-
src/runtime/contrib/miopen/softmax.cc | 6 +-
src/runtime/contrib/mrvl/mrvl_base64.h | 4 +-
src/runtime/contrib/mrvl/mrvl_hw_runtime.cc | 24 +-
src/runtime/contrib/mrvl/mrvl_runtime.cc | 9 +-
src/runtime/contrib/mrvl/mrvl_sw_runtime_lib.cc | 8 +-
src/runtime/contrib/msc/tensorrt_runtime.cc | 23 +-
src/runtime/contrib/nnapi/nnapi_builder.cc | 80 ++--
src/runtime/contrib/nnapi/nnapi_ops.cc | 53 +--
src/runtime/contrib/nnapi/nnapi_runtime.cc | 45 +-
src/runtime/contrib/nvshmem/init.cc | 14 +-
src/runtime/contrib/nvshmem/memory_allocator.cc | 7 +-
src/runtime/contrib/papi/papi.cc | 29 +-
src/runtime/contrib/random/mt_random_engine.cc | 27 +-
src/runtime/contrib/random/random.cc | 49 +--
src/runtime/contrib/rocblas/rocblas.cc | 30 +-
src/runtime/contrib/sort/sort.cc | 64 +--
src/runtime/contrib/tensorrt/tensorrt_builder.cc | 44 +-
src/runtime/contrib/tensorrt/tensorrt_calibrator.h | 6 +-
src/runtime/contrib/tensorrt/tensorrt_ops.cc | 196 ++++-----
src/runtime/contrib/tensorrt/tensorrt_runtime.cc | 28 +-
src/runtime/contrib/tflite/tflite_runtime.cc | 80 ++--
src/runtime/contrib/tflite/tflite_runtime.h | 2 +-
src/runtime/cuda/cuda_common.h | 14 +-
src/runtime/cuda/cuda_device_api.cc | 45 +-
src/runtime/cuda/cuda_module.cc | 22 +-
src/runtime/cuda/l2_cache_flush.cc | 2 +-
src/runtime/device_api.cc | 16 +-
src/runtime/disco/bcast_session.cc | 11 +-
src/runtime/disco/builtin.cc | 13 +-
src/runtime/disco/cuda_ipc/cuda_ipc_memory.cc | 8 +-
src/runtime/disco/cuda_ipc/custom_allreduce.cc | 4 +-
src/runtime/disco/disco_worker.cc | 10 +-
src/runtime/disco/distributed/socket_session.cc | 22 +-
src/runtime/disco/loader.cc | 50 +--
src/runtime/disco/message_queue.h | 6 +-
src/runtime/disco/nccl/nccl.cc | 111 ++---
src/runtime/disco/nccl/nccl_context.h | 16 +-
src/runtime/disco/process_session.cc | 22 +-
src/runtime/disco/protocol.h | 37 +-
src/runtime/disco/threaded_session.cc | 4 +-
src/runtime/disco/utils.h | 3 +-
src/runtime/file_utils.cc | 28 +-
src/runtime/file_utils.h | 14 +-
src/runtime/hexagon/hexagon_buffer.cc | 21 +-
src/runtime/hexagon/hexagon_buffer_manager.h | 4 +-
src/runtime/hexagon/hexagon_device_api.cc | 81 ++--
src/runtime/hexagon/hexagon_device_api.h | 27 +-
src/runtime/hexagon/hexagon_htp.cc | 8 +-
src/runtime/hexagon/hexagon_hvx.cc | 9 +-
src/runtime/hexagon/hexagon_module.cc | 13 +-
src/runtime/hexagon/hexagon_thread_manager.cc | 24 +-
src/runtime/hexagon/hexagon_thread_manager.h | 2 +-
src/runtime/hexagon/hexagon_user_dma.cc | 2 +-
src/runtime/hexagon/hexagon_vtcm_pool.cc | 31 +-
src/runtime/hexagon/hexagon_vtcm_pool.h | 4 +-
src/runtime/hexagon/ops/conv2d_fp16_hvx.cc | 39 +-
src/runtime/hexagon/ops/conv2d_quant_hvx.cc | 40 +-
src/runtime/hexagon/qhl/qhl_wrapper.cc | 8 +-
src/runtime/hexagon/ring_buffer.h | 22 +-
src/runtime/hexagon/rpc/android/session.cc | 17 +-
src/runtime/hexagon/rpc/hexagon/rpc_server.cc | 4 +-
src/runtime/hexagon/rpc/simulator/rpc_server.cc | 10 +-
src/runtime/hexagon/rpc/simulator/session.cc | 82 ++--
src/runtime/logging.cc | 17 +-
src/runtime/memory/memory_manager.cc | 23 +-
src/runtime/memory/pooled_allocator.h | 2 +-
src/runtime/metal/metal_common.h | 6 +-
src/runtime/module.cc | 2 +-
src/runtime/opencl/opencl_common.h | 17 +-
src/runtime/opencl/opencl_device_api.cc | 34 +-
src/runtime/opencl/opencl_module.cc | 36 +-
src/runtime/opencl/opencl_module_spirv.cc | 4 +-
.../opencl/opencl_wrapper/opencl_wrapper.cc | 2 +-
src/runtime/pack_args.h | 10 +-
src/runtime/profiling.cc | 109 ++---
src/runtime/rocm/rocm_common.h | 21 +-
src/runtime/rocm/rocm_device_api.cc | 4 +-
src/runtime/rocm/rocm_module.cc | 12 +-
src/runtime/rpc/rpc_channel.cc | 4 +-
src/runtime/rpc/rpc_device_api.cc | 6 +-
src/runtime/rpc/rpc_endpoint.cc | 109 ++---
src/runtime/rpc/rpc_event_impl.cc | 5 +-
src/runtime/rpc/rpc_local_session.cc | 4 +-
src/runtime/rpc/rpc_module.cc | 52 +--
src/runtime/rpc/rpc_pipe_impl.cc | 8 +-
src/runtime/rpc/rpc_server_env.cc | 2 +-
src/runtime/rpc/rpc_session.cc | 6 +-
src/runtime/rpc/rpc_socket_impl.cc | 22 +-
src/runtime/static_library.cc | 4 +-
src/runtime/tensor.cc | 51 +--
src/runtime/texture.h | 7 +-
src/runtime/thread_pool.cc | 10 +-
src/runtime/thread_storage_scope.h | 10 +-
src/runtime/threading_backend.cc | 10 +-
src/runtime/vm/attn_backend.cc | 26 +-
src/runtime/vm/attn_backend.h | 34 +-
src/runtime/vm/attn_utils.h | 22 +-
src/runtime/vm/builtin.cc | 110 ++---
src/runtime/vm/cuda/cuda_graph_builtin.cc | 4 +-
src/runtime/vm/executable.cc | 35 +-
src/runtime/vm/hexagon/builtin.cc | 8 +-
src/runtime/vm/kv_state.cc | 2 +-
src/runtime/vm/lm_support.cc | 107 ++---
src/runtime/vm/paged_kv_cache.cc | 409 +++++++++---------
src/runtime/vm/rnn_state.cc | 73 ++--
src/runtime/vm/tensor_cache_support.cc | 37 +-
src/runtime/vm/vm.cc | 97 ++---
src/runtime/vulkan/vulkan_common.cc | 2 +-
src/runtime/vulkan/vulkan_common.h | 8 +-
src/runtime/vulkan/vulkan_device.cc | 47 ++-
src/runtime/vulkan/vulkan_device_api.cc | 29 +-
src/runtime/vulkan/vulkan_module.cc | 4 +-
src/runtime/vulkan/vulkan_stream.cc | 10 +-
src/runtime/vulkan/vulkan_wrapped_func.cc | 14 +-
src/runtime/workspace_pool.cc | 5 +-
src/s_tir/analysis/calculate_allocated_memory.cc | 16 +-
src/s_tir/analysis/estimate_flops.cc | 4 +-
src/s_tir/analysis/find_anchor_sblock.cc | 5 +-
src/s_tir/analysis/identify_memcpy.cc | 2 +-
src/s_tir/analysis/is_pure_function.cc | 16 +-
src/s_tir/analysis/oob_checker.cc | 3 +-
.../analysis/sblock_access_region_detector.cc | 13 +-
.../analysis/sblock_buffer_access_lca_detector.cc | 4 +-
src/s_tir/analysis/verify_gpu_code.cc | 12 +-
src/s_tir/backend/adreno/inject_texture_alloc.cc | 7 +-
src/s_tir/backend/adreno/texture_flatten.cc | 4 +-
src/s_tir/data_layout.cc | 66 +--
src/s_tir/meta_schedule/arg_info.cc | 26 +-
src/s_tir/meta_schedule/cost_model/cost_model.cc | 12 +-
src/s_tir/meta_schedule/database/database.cc | 14 +-
src/s_tir/meta_schedule/database/database_utils.cc | 37 +-
src/s_tir/meta_schedule/database/json_database.cc | 25 +-
.../meta_schedule/database/memory_database.cc | 2 +-
.../database/ordered_union_database.cc | 12 +-
.../meta_schedule/database/schedule_fn_database.cc | 12 +-
src/s_tir/meta_schedule/database/union_database.cc | 12 +-
.../feature_extractor/feature_extractor.cc | 8 +-
.../feature_extractor/per_store_feature.cc | 20 +-
.../measure_callback/add_to_database.cc | 2 +-
.../measure_callback/measure_callback.cc | 7 +-
.../measure_callback/update_cost_model.cc | 7 +-
src/s_tir/meta_schedule/module_equality.cc | 2 +-
.../mutator/mutate_compute_location.cc | 4 +-
src/s_tir/meta_schedule/mutator/mutate_parallel.cc | 12 +-
.../meta_schedule/mutator/mutate_thread_binding.cc | 14 +-
.../meta_schedule/mutator/mutate_tile_size.cc | 12 +-
src/s_tir/meta_schedule/mutator/mutate_unroll.cc | 10 +-
src/s_tir/meta_schedule/mutator/mutator.cc | 10 +-
.../postproc/disallow_async_strided_mem_copy.cc | 2 +-
src/s_tir/meta_schedule/postproc/postproc.cc | 10 +-
.../postproc/rewrite_cooperative_fetch.cc | 12 +-
src/s_tir/meta_schedule/postproc/rewrite_layout.cc | 8 +-
.../postproc/rewrite_parallel_vectorize_unroll.cc | 10 +-
.../postproc/rewrite_reduction_block.cc | 2 +-
.../meta_schedule/postproc/rewrite_tensorize.cc | 4 +-
.../postproc/rewrite_unbound_block.cc | 8 +-
.../meta_schedule/postproc/verify_gpu_code.cc | 8 +-
.../meta_schedule/postproc/verify_vtcm_limit.cc | 4 +-
src/s_tir/meta_schedule/profiler.cc | 9 +-
src/s_tir/meta_schedule/schedule/cpu/winograd.cc | 10 +-
.../meta_schedule/schedule/cuda/thread_bind.cc | 6 +-
src/s_tir/meta_schedule/schedule/cuda/winograd.cc | 20 +-
.../meta_schedule/schedule/generic/winograd.cc | 2 +-
.../meta_schedule/schedule_rule/add_rfactor.cc | 4 +-
.../schedule_rule/apply_custom_rule.cc | 7 +-
src/s_tir/meta_schedule/schedule_rule/auto_bind.cc | 8 +-
.../meta_schedule/schedule_rule/auto_inline.cc | 2 +-
.../schedule_rule/cross_thread_reduction.cc | 15 +-
.../schedule_rule/multi_level_tiling.cc | 8 +-
.../schedule_rule/multi_level_tiling.h | 6 +-
.../multi_level_tiling_tensor_core.cc | 49 ++-
.../multi_level_tiling_wide_vector.cc | 2 +-
.../multi_level_tiling_with_intrin.cc | 4 +-
.../schedule_rule/parallel_vectorize_unroll.cc | 2 +-
.../schedule_rule/random_compute_location.cc | 2 +-
.../meta_schedule/schedule_rule/schedule_rule.cc | 10 +-
.../search_strategy/evolutionary_search.cc | 69 +--
.../meta_schedule/search_strategy/replay_func.cc | 23 +-
.../meta_schedule/search_strategy/replay_trace.cc | 20 +-
.../search_strategy/search_strategy.cc | 13 +-
.../space_generator/post_order_apply.cc | 2 +-
.../meta_schedule/space_generator/schedule_fn.cc | 12 +-
.../space_generator/space_generator.cc | 10 +-
.../meta_schedule/task_scheduler/task_scheduler.cc | 42 +-
src/s_tir/meta_schedule/trace_apply.cc | 12 +-
src/s_tir/meta_schedule/tune_context.cc | 3 +-
src/s_tir/meta_schedule/utils.h | 29 +-
src/s_tir/schedule/analysis/analysis.cc | 57 +--
src/s_tir/schedule/analysis/layout.cc | 10 +-
src/s_tir/schedule/analysis/reducer.cc | 40 +-
src/s_tir/schedule/analysis/verify.cc | 66 +--
src/s_tir/schedule/concrete_schedule.cc | 21 +-
src/s_tir/schedule/concrete_schedule.h | 20 +-
src/s_tir/schedule/instruction.cc | 8 +-
src/s_tir/schedule/instruction_traits.h | 20 +-
src/s_tir/schedule/ir_comparator.cc | 8 +-
src/s_tir/schedule/primitive/annotate.cc | 20 +-
.../schedule/primitive/annotate_buffer_access.cc | 7 +-
src/s_tir/schedule/primitive/blockize_tensorize.cc | 34 +-
src/s_tir/schedule/primitive/cache_index.cc | 8 +-
src/s_tir/schedule/primitive/cache_read_write.cc | 41 +-
src/s_tir/schedule/primitive/compute_at.cc | 32 +-
src/s_tir/schedule/primitive/compute_inline.cc | 10 +-
src/s_tir/schedule/primitive/decompose_padding.cc | 8 +-
src/s_tir/schedule/primitive/for_kind.cc | 2 +-
src/s_tir/schedule/primitive/get_block_loop.cc | 6 +-
src/s_tir/schedule/primitive/hide_buffer_access.cc | 2 +-
.../schedule/primitive/layout_transformation.cc | 48 +--
.../schedule/primitive/loop_transformation.cc | 20 +-
src/s_tir/schedule/primitive/pad_einsum.cc | 4 +-
src/s_tir/schedule/primitive/read_write_at.cc | 8 +-
src/s_tir/schedule/primitive/reduction.cc | 14 +-
src/s_tir/schedule/primitive/rolling_buffer.cc | 2 +-
src/s_tir/schedule/primitive/sampling.cc | 40 +-
src/s_tir/schedule/schedule.cc | 58 +--
src/s_tir/schedule/state.cc | 52 +--
src/s_tir/schedule/trace.cc | 69 +--
src/s_tir/schedule/traced_schedule.cc | 7 +-
src/s_tir/schedule/transform.cc | 20 +-
src/s_tir/schedule/utils.h | 11 +-
src/s_tir/transform/annotate_irregular_loop.cc | 4 +-
src/s_tir/transform/bound_checker.cc | 2 +-
src/s_tir/transform/canonicalize_loop.cc | 3 +-
src/s_tir/transform/compact_buffer_region.cc | 22 +-
src/s_tir/transform/convert_blocks_to_opaque.cc | 8 +-
src/s_tir/transform/default_gpu_schedule.cc | 9 +-
src/s_tir/transform/hoist_expression.cc | 6 +-
src/s_tir/transform/inject_double_buffer.cc | 34 +-
src/s_tir/transform/inject_permuted_layout.cc | 20 +-
src/s_tir/transform/inject_ptx_async_copy.cc | 12 +-
src/s_tir/transform/inject_software_pipeline.cc | 54 +--
src/s_tir/transform/inject_virtual_thread.cc | 27 +-
src/s_tir/transform/loop_partition.cc | 16 +-
src/s_tir/transform/lower_async_dma.cc | 4 +-
.../transform/lower_cross_thread_reduction.cc | 27 +-
src/s_tir/transform/lower_match_buffer.cc | 31 +-
src/s_tir/transform/lower_opaque_block.cc | 11 +-
src/s_tir/transform/lower_thread_allreduce.cc | 45 +-
src/s_tir/transform/lower_vtcm_alloc.cc | 2 +-
.../manifest_shared_memory_local_stage.cc | 36 +-
src/s_tir/transform/memhammer_coalesce.cc | 6 +-
.../transform/memhammer_intermediate_stage.cc | 12 +-
src/s_tir/transform/memhammer_lower_auto_copy.cc | 6 +-
.../transform/memhammer_tensorcore_rewrite.cc | 8 +-
.../transform/merge_shared_memory_allocations.cc | 31 +-
.../plan_update_buffer_allocation_location.cc | 8 +-
src/s_tir/transform/remove_store_undef.cc | 15 +-
.../remove_weight_layout_rewrite_block.cc | 10 +-
src/s_tir/transform/renew_defs.cc | 10 +-
src/s_tir/transform/storage_access.cc | 18 +-
src/s_tir/transform/tensorcore_infer_fragment.cc | 56 +--
src/s_tir/transform/thread_storage_sync.cc | 16 +-
src/s_tir/transform/transform_mma_buffer_layout.cc | 22 +-
src/s_tir/transform/unify_thread_binding.cc | 8 +-
.../transform/using_assume_to_reduce_branches.cc | 24 +-
src/script/ir_builder/base.cc | 18 +-
src/script/ir_builder/ir/frame.cc | 6 +-
src/script/ir_builder/ir/ir.cc | 28 +-
src/script/ir_builder/ir/utils.h | 10 +-
src/script/ir_builder/relax/distributed.cc | 7 +-
src/script/ir_builder/relax/frame.cc | 59 +--
src/script/ir_builder/relax/ir.cc | 41 +-
src/script/ir_builder/relax/utils.h | 28 +-
src/script/ir_builder/tir/frame.cc | 33 +-
src/script/ir_builder/tir/ir.cc | 113 ++---
src/script/ir_builder/tir/utils.h | 45 +-
src/script/printer/doc.cc | 12 +-
src/script/printer/doc_printer/base_doc_printer.cc | 2 +-
.../printer/doc_printer/python_doc_printer.cc | 38 +-
src/script/printer/ir/ir.cc | 12 +-
src/script/printer/ir_docsifier.cc | 8 +-
src/script/printer/relax/call.cc | 16 +-
src/script/printer/relax/distributed.cc | 2 +-
src/script/printer/relax/region.cc | 6 +-
src/script/printer/relax/tir.cc | 20 +-
src/script/printer/tir/block.cc | 8 +-
src/script/printer/tir/buffer.cc | 6 +-
src/script/printer/tir/expr.cc | 8 +-
src/script/printer/tir/for_loop.cc | 6 +-
src/script/printer/tir/function.cc | 2 +-
src/script/printer/tir/stmt.cc | 4 +-
src/script/printer/utils.h | 2 +-
src/support/base64.h | 18 +-
src/support/ffi_testing.cc | 27 +-
src/support/nd_int_set.h | 6 +-
src/support/parallel_for.cc | 21 +-
src/support/pipe.h | 18 +-
src/support/ring_buffer.h | 4 +-
src/support/scalars.cc | 22 +-
src/support/socket.h | 28 +-
src/support/table_printer.h | 2 +-
src/target/build_common.h | 3 +-
src/target/canonicalizer/llvm/arm_aprofile.cc | 2 +-
src/target/canonicalizer/llvm/canonicalize.cc | 4 +-
src/target/codegen.cc | 37 +-
src/target/datatype/registry.cc | 6 +-
src/target/intrin_rule.cc | 40 +-
src/target/intrin_rule.h | 8 +-
src/target/llvm/codegen_aarch64.cc | 16 +-
src/target/llvm/codegen_amdgpu.cc | 48 ++-
src/target/llvm/codegen_arm.cc | 2 +-
src/target/llvm/codegen_cpu.cc | 70 ++--
src/target/llvm/codegen_hexagon.cc | 36 +-
src/target/llvm/codegen_llvm.cc | 158 +++----
src/target/llvm/codegen_nvptx.cc | 35 +-
src/target/llvm/codegen_params.cc | 29 +-
src/target/llvm/codegen_x86_64.cc | 6 +-
src/target/llvm/intrin_rule_hexagon.cc | 16 +-
src/target/llvm/intrin_rule_llvm.cc | 26 +-
src/target/llvm/intrin_rule_llvm.h | 8 +-
src/target/llvm/intrin_rule_nvptx.cc | 8 +-
src/target/llvm/intrin_rule_rocm.cc | 14 +-
src/target/llvm/llvm_instance.cc | 31 +-
src/target/llvm/llvm_module.cc | 66 +--
src/target/opt/build_cuda_off.cc | 2 +-
src/target/opt/build_cuda_on.cc | 8 +-
src/target/opt/build_opencl_off.cc | 2 +-
src/target/source/codegen_c.cc | 98 ++---
src/target/source/codegen_c_host.cc | 20 +-
src/target/source/codegen_cuda.cc | 155 +++----
src/target/source/codegen_metal.cc | 50 +--
src/target/source/codegen_opencl.cc | 40 +-
src/target/source/codegen_params.cc | 24 +-
src/target/source/codegen_source_base.cc | 12 +-
src/target/source/codegen_webgpu.cc | 102 ++---
src/target/source/intrin_rule_cuda.cc | 6 +-
src/target/source/intrin_rule_metal.cc | 6 +-
src/target/source/intrin_rule_opencl.cc | 6 +-
src/target/source/ptx.cc | 60 +--
src/target/source/source_module.cc | 22 +-
src/target/spirv/codegen_spirv.cc | 143 ++++---
src/target/spirv/codegen_spirv.h | 15 +-
src/target/spirv/intrin_rule_spirv.cc | 10 +-
src/target/spirv/ir_builder.cc | 103 ++---
src/target/spirv/ir_builder.h | 6 +-
src/target/spirv/spirv_support.cc | 2 +-
src/target/spirv/spirv_utils.cc | 21 +-
src/target/tag.cc | 2 +-
src/target/target.cc | 26 +-
src/target/target_kind.cc | 17 +-
src/target/virtual_device.cc | 6 +-
src/te/operation/compute_op.cc | 33 +-
src/te/operation/create_primfunc.cc | 49 +--
src/te/operation/extern_op.cc | 10 +-
src/te/operation/placeholder_op.cc | 6 +-
src/te/operation/scan_op.cc | 22 +-
src/te/tensor.cc | 2 +-
src/tir/analysis/control_flow_graph.cc | 48 ++-
src/tir/analysis/var_use_def_analysis.cc | 19 +-
src/tir/analysis/verify_memory.cc | 8 +-
src/tir/analysis/verify_ssa.cc | 3 +-
src/tir/analysis/verify_well_formed.cc | 64 ++-
src/tir/ir/buffer.cc | 55 ++-
src/tir/ir/data_type_rewriter.cc | 30 +-
src/tir/ir/expr.cc | 197 ++++-----
src/tir/ir/function.cc | 22 +-
src/tir/ir/index_map.cc | 35 +-
src/tir/ir/script/script_complete.cc | 6 +-
src/tir/ir/specialize.cc | 59 +--
src/tir/ir/stmt.cc | 129 +++---
src/tir/ir/stmt_functor.cc | 11 +-
src/tir/ir/tir_visitor_with_path.cc | 2 +-
src/tir/ir/transform.cc | 2 +-
src/tir/op/op.cc | 120 +++---
src/tir/transform/annotate_device_regions.cc | 2 +-
src/tir/transform/arg_binder.cc | 23 +-
src/tir/transform/dtype_conversion.cc | 6 +-
src/tir/transform/dtype_conversion.h | 8 +-
src/tir/transform/flatten_buffer.cc | 12 +-
src/tir/transform/force_narrow_index_to_i32.cc | 12 +-
src/tir/transform/inline_private_functions.cc | 4 +-
src/tir/transform/ir_utils.cc | 44 +-
src/tir/transform/ir_utils.h | 10 +-
src/tir/transform/lower_custom_datatypes.cc | 47 ++-
src/tir/transform/lower_device_kernel_launch.cc | 34 +-
src/tir/transform/lower_intrin.cc | 10 +-
src/tir/transform/lower_tvm_builtin.cc | 46 +-
src/tir/transform/lower_warp_memory.cc | 45 +-
src/tir/transform/make_packed_api.cc | 20 +-
src/tir/transform/narrow_datatype.cc | 6 +-
src/tir/transform/remap_thread_axis.cc | 6 +-
src/tir/transform/remove_no_op.cc | 2 +-
src/tir/transform/simplify.cc | 2 +-
src/tir/transform/storage_rewrite.cc | 86 ++--
src/tir/transform/unroll_loop.cc | 4 +-
src/tir/transform/unsupported_dtype_legalize.cc | 36 +-
src/tir/transform/update_pointer_storage_scope.cc | 2 +-
src/tir/transform/vectorize_loop.cc | 52 +--
src/topi/einsum.cc | 25 +-
src/topi/transform.cc | 4 +-
tests/cpp-runtime/hexagon/hexagon_buffer_tests.cc | 16 +-
.../hexagon/hexagon_device_api_tests.cc | 67 +--
.../hexagon/hexagon_thread_manager_tests.cc | 70 ++--
.../cpp-runtime/hexagon/hexagon_vtcm_pool_tests.cc | 63 +--
tests/cpp-runtime/hexagon/ring_buffer_tests.cc | 18 +-
tests/cpp-runtime/opencl/opencl_nativeptr.cc | 8 +-
tests/cpp-runtime/opencl/opencl_timer_test.cc | 2 +-
tests/cpp-runtime/opencl/texture_copy_test.cc | 50 +--
tests/cpp/arith_simplify_test.cc | 8 +-
tests/cpp/expr_test.cc | 10 +-
tests/cpp/ir_functor_test.cc | 70 ++--
tests/cpp/ndarray_test.cc | 8 +-
tests/cpp/nested_msg_test.cc | 2 +-
tests/cpp/object_protocol_test.cc | 36 +-
tests/cpp/parallel_for_test.cc | 29 +-
tests/cpp/pattern_match_test.cc | 131 +++---
tests/cpp/random_engine_test.cc | 8 +-
tests/cpp/runtime/logging_test.cc | 6 +-
tests/cpp/support/ring_buffer_test.cc | 8 +-
tests/cpp/support/scalars_test.cc | 16 +-
.../cpp/target/canonicalizer/arm_aprofile_test.cc | 4 +-
tests/cpp/target_test.cc | 44 +-
tests/cpp/tir_analysis_side_effect.cc | 9 +-
tests/cpp/tir_scalable_datatype.cc | 16 +-
.../test_runtime_ndarray.py | 1 -
.../test_runtime_packed_func.py | 1 -
.../python/arith/test_arith_canonical_simplify.py | 106 ++---
tests/python/arith/test_arith_const_int_bound.py | 65 ++-
tests/python/arith/test_arith_deduce_bound.py | 38 +-
tests/python/arith/test_arith_detect_clip_bound.py | 11 +-
.../arith/test_arith_detect_linear_equation.py | 11 +-
tests/python/arith/test_arith_domain_touched.py | 1 -
tests/python/arith/test_arith_intset.py | 32 +-
tests/python/arith/test_arith_modular_set.py | 41 +-
tests/python/arith/test_arith_rewrite_simplify.py | 462 +++++++++++----------
.../arith/test_arith_solve_linear_equations.py | 14 +-
.../arith/test_arith_solve_linear_inequality.py | 20 +-
.../python/codegen/test_target_codegen_llvm_vla.py | 1 -
.../codegen/test_target_codegen_static_init.py | 1 -
tests/python/ir/test_ir_container.py | 18 +-
tests/python/relax/frontend_nn_extern_module.cc | 44 +-
.../test_s_tir_transform_compact_buffer_region.py | 1 -
.../test_s_tir_transform_decorate_device_scope.py | 3 +-
.../transform/test_s_tir_transform_hoist_if.py | 2 +-
.../test_s_tir_transform_loop_partition.py | 1 -
...s_tir_transform_lower_cross_thread_reduction.py | 2 +-
.../test_s_tir_transform_lower_init_block.py | 2 +-
.../test_s_tir_transform_lower_opaque_block.py | 1 -
...st_s_tir_transform_memhammer_lower_auto_copy.py | 2 +-
...form_merge_dynamic_shared_memory_allocations.py | 2 +-
...sform_plan_update_buffer_allocation_location.py | 1 -
.../test_s_tir_transform_profiling_instr.py | 2 +-
.../transform/test_s_tir_transform_thread_sync.py | 2 +-
.../test_s_tir_transform_unify_thread_binding.py | 2 +-
tests/python/testing/test_testing.py | 1 -
.../test_tir_analysis_expr_deep_equal.py | 7 +-
.../tir-analysis/test_tir_analysis_verify_ssa.py | 7 +-
tests/python/tir-base/test_tir_buffer.py | 45 +-
tests/python/tir-base/test_tir_constructor.py | 13 +-
tests/python/tir-base/test_tir_intrin.py | 2 +-
tests/python/tir-base/test_tir_nodes.py | 74 ++--
tests/python/tir-base/test_tir_ops.py | 31 +-
.../tir-base/test_tir_structural_equal_hash.py | 50 +--
.../test_tir_transform_common_subexpr_elim.py | 67 ++-
.../test_tir_transform_convert_ssa.py | 11 +-
.../test_tir_transform_flatten_buffer.py | 1 -
.../test_tir_transform_lower_intrin.py | 75 ++--
.../test_tir_transform_make_packed_api.py | 2 +-
.../test_tir_transform_narrow_datatype.py | 1 -
.../test_tir_transform_prim_func_pass.py | 7 +-
.../test_tir_transform_remove_no_op.py | 11 +-
.../test_tir_transform_split_host_device.py | 1 -
.../test_tir_transform_storage_rewrite.py | 1 -
web/emcc/tvmjs_support.cc | 12 +-
web/emcc/wasm_runtime.cc | 12 +-
web/emcc/webgpu_runtime.cc | 28 +-
785 files changed, 9107 insertions(+), 8707 deletions(-)
