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 86b391a4b6 [FFI] Support inline module (#18271)
add 5c1707d277 [FFI] Construct NDArray.strides by default (#18272)
add e1700e1a22 [FFI][ABI] Append symbol prefix for ffi exported functions
(#18273)
add d3a5811ba8 [FFI] Update the interface of `ffi.load_inline` to match
torch (#18274)
add 3c36ce2ec6 [FFI][REFACTOR][ABI] Rename NDArray to Tensor (#18275)
add 58ab25e809 [FFI] Add ffi::Tensor.strides() (#18276)
No new revisions were added by this update.
Summary of changes:
apps/android_rpc/app/src/main/jni/tvm_runtime.h | 4 +-
apps/android_rpc/tests/android_rpc_test.py | 4 +-
apps/hexagon_launcher/launcher_core.h | 2 +-
apps/hexagon_launcher/launcher_hexagon.cc | 12 +-
apps/ios_rpc/tests/ios_rpc_test.py | 4 +-
docs/arch/index.rst | 6 +-
docs/deep_dive/tensor_ir/tutorials/tir_creation.py | 6 +-
.../tensor_ir/tutorials/tir_transformation.py | 6 +-
docs/get_started/tutorials/ir_module.py | 6 +-
docs/get_started/tutorials/quick_start.py | 16 +-
docs/how_to/tutorials/cross_compilation_and_rpc.py | 8 +-
docs/how_to/tutorials/customize_opt.py | 4 +-
docs/how_to/tutorials/e2e_opt_model.py | 4 +-
docs/how_to/tutorials/optimize_llm.py | 6 +-
docs/reference/api/python/index.rst | 1 -
docs/reference/api/python/runtime/ndarray.rst | 21 --
docs/reference/api/python/runtime/runtime.rst | 1 -
ffi/CMakeLists.txt | 4 +-
ffi/docs/.gitignore | 1 +
ffi/docs/Makefile | 6 +-
ffi/docs/concepts/abi_overview.md | 12 +-
ffi/docs/conf.py | 3 +
ffi/docs/get_started/quick_start.md | 2 +-
ffi/docs/guides/cpp_guide.md | 32 +--
ffi/docs/guides/python_guide.md | 8 +-
ffi/examples/inline_module/main.py | 13 +-
ffi/examples/packaging/src/extension.cc | 3 +-
ffi/examples/quick_start/run_example.py | 4 +-
ffi/examples/quick_start/src/add_one_cpu.cc | 4 +-
ffi/examples/quick_start/src/add_one_cuda.cu | 3 +-
ffi/examples/quick_start/src/run_example.cc | 10 +-
ffi/include/tvm/ffi/c_api.h | 34 +--
ffi/include/tvm/ffi/container/shape.h | 13 +-
.../tvm/ffi/container/{ndarray.h => tensor.h} | 142 +++++-----
ffi/include/tvm/ffi/extra/module.h | 15 +-
ffi/include/tvm/ffi/extra/structural_equal.h | 9 +-
ffi/include/tvm/ffi/extra/structural_hash.h | 4 +-
ffi/include/tvm/ffi/function.h | 26 +-
ffi/include/tvm/ffi/object.h | 2 +-
ffi/include/tvm/ffi/type_traits.h | 8 +-
ffi/pyproject.toml | 2 +-
ffi/python/tvm_ffi/__init__.py | 8 +-
ffi/python/tvm_ffi/cpp/load_inline.py | 136 +++++----
ffi/python/tvm_ffi/cython/base.pxi | 12 +-
ffi/python/tvm_ffi/cython/core.pyx | 2 +-
ffi/python/tvm_ffi/cython/function.pxi | 37 +--
.../tvm_ffi/cython/{ndarray.pxi => tensor.pxi} | 50 ++--
ffi/python/tvm_ffi/module.py | 25 +-
ffi/python/tvm_ffi/{ndarray.py => tensor.py} | 6 +-
ffi/src/ffi/extra/library_module.cc | 4 +-
ffi/src/ffi/extra/library_module_dynamic_lib.cc | 2 +-
ffi/src/ffi/extra/library_module_system_lib.cc | 17 +-
ffi/src/ffi/extra/module_internal.h | 12 +-
ffi/src/ffi/extra/structural_equal.cc | 24 +-
ffi/src/ffi/extra/structural_hash.cc | 32 +--
ffi/src/ffi/{ndarray.cc => tensor.cc} | 32 +--
ffi/tests/cpp/test_example.cc | 20 +-
ffi/tests/cpp/{test_ndarray.cc => test_tensor.cc} | 64 +++--
ffi/tests/python/test_function.py | 22 +-
ffi/tests/python/test_load_inline.py | 140 ++++++++--
.../python/{test_ndarray.py => test_tensor.py} | 8 +-
include/tvm/ir/module.h | 8 +-
include/tvm/meta_schedule/builder.h | 6 +-
include/tvm/meta_schedule/database.h | 8 +-
include/tvm/meta_schedule/feature_extractor.h | 16 +-
include/tvm/node/structural_hash.h | 2 +-
include/tvm/relax/expr.h | 4 +-
include/tvm/runtime/disco/builtin.h | 34 +--
include/tvm/runtime/disco/session.h | 24 +-
include/tvm/runtime/memory/memory_manager.h | 24 +-
include/tvm/runtime/object.h | 4 +-
include/tvm/runtime/profiling.h | 14 +-
include/tvm/runtime/serializer.h | 2 +-
include/tvm/runtime/{ndarray.h => tensor.h} | 88 +++---
...rray_cache_support.h => tensor_cache_support.h} | 34 +--
include/tvm/script/ir_builder/tir/frame.h | 2 +-
include/tvm/script/ir_builder/tir/ir.h | 4 +-
include/tvm/tir/builtin.h | 2 +-
include/tvm/tir/function.h | 2 +-
include/tvm/tir/index_map.h | 8 +-
include/tvm/tir/stmt.h | 4 +-
include/tvm/tir/transform.h | 14 +-
include/tvm/topi/transform.h | 14 +-
jvm/README.md | 8 +-
.../src/main/java/org/apache/tvm/Function.java | 18 +-
jvm/core/src/main/java/org/apache/tvm/LibInfo.java | 4 +-
jvm/core/src/main/java/org/apache/tvm/Module.java | 2 +-
jvm/core/src/main/java/org/apache/tvm/TVMType.java | 2 +-
.../src/main/java/org/apache/tvm/TVMValue.java | 2 +-
.../org/apache/tvm/{NDArray.java => Tensor.java} | 56 ++--
.../tvm/{NDArrayBase.java => TensorBase.java} | 12 +-
.../src/main/java/org/apache/tvm/TypeIndex.java | 2 +-
.../src/test/java/org/apache/tvm/FunctionTest.java | 8 +-
.../src/test/java/org/apache/tvm/ModuleTest.java | 8 +-
.../src/test/java/org/apache/tvm/NDArrayTest.java | 80 ------
.../src/test/java/org/apache/tvm/TensorTest.java | 80 ++++++
jvm/native/src/main/native/jni_helper_func.h | 10 +-
.../src/main/native/org_apache_tvm_native_c_api.cc | 17 +-
python/tvm/__init__.py | 6 +-
python/tvm/contrib/cudnn.py | 2 +-
python/tvm/contrib/dlpack.py | 4 +-
python/tvm/contrib/hexagon/generate_take_op.py | 2 +-
python/tvm/contrib/hexagon/meta_schedule.py | 6 +-
python/tvm/contrib/hexagon/tools.py | 4 +-
python/tvm/contrib/miopen.py | 2 +-
python/tvm/contrib/msc/core/codegen/codegen.py | 2 +-
python/tvm/contrib/msc/core/frontend/translate.py | 18 +-
python/tvm/contrib/msc/core/runtime/hook.py | 8 +-
python/tvm/contrib/msc/core/runtime/runner.py | 56 ++--
.../contrib/msc/core/tools/distill/distiller.py | 10 +-
python/tvm/contrib/msc/core/tools/prune/pruner.py | 18 +-
python/tvm/contrib/msc/core/tools/tool.py | 24 +-
python/tvm/contrib/msc/core/transform/transform.py | 4 +-
python/tvm/contrib/msc/core/utils/info.py | 14 +-
.../msc/framework/tensorflow/codegen/codegen.py | 2 +-
.../msc/framework/tensorflow/frontend/translate.py | 2 +-
.../msc/framework/tensorflow/runtime/runner.py | 4 +-
.../msc/framework/tensorrt/codegen/codegen.py | 4 +-
.../msc/framework/tensorrt/frontend/translate.py | 4 +-
.../msc/framework/tensorrt/runtime/runner.py | 6 +-
.../framework/tensorrt/tools/quantize/quantizer.py | 8 +-
.../contrib/msc/framework/torch/codegen/codegen.py | 2 +-
.../msc/framework/torch/frontend/translate.py | 2 +-
.../contrib/msc/framework/torch/runtime/runner.py | 8 +-
.../contrib/msc/framework/tvm/codegen/codegen.py | 2 +-
.../contrib/msc/framework/tvm/runtime/runner.py | 8 +-
.../msc/framework/tvm/tools/quantize/method.py | 4 +-
.../msc/framework/tvm/tools/quantize/quantizer.py | 4 +-
.../msc/framework/tvm/tools/track/tracker.py | 4 +-
python/tvm/contrib/tflite_runtime.py | 4 +-
python/tvm/contrib/tvmjs.py | 30 +-
python/tvm/dlight/benchmark/bench.py | 6 +-
python/tvm/exec/disco_worker.py | 18 +-
python/tvm/exec/rpc_proxy.py | 2 +-
python/tvm/ir/base.py | 6 +-
python/tvm/meta_schedule/builder/builder.py | 10 +-
python/tvm/meta_schedule/builder/local_builder.py | 16 +-
python/tvm/meta_schedule/cost_model/mlp_model.py | 4 +-
python/tvm/meta_schedule/cost_model/xgb_model.py | 4 +-
python/tvm/meta_schedule/database/json_database.py | 4 +-
.../tvm/meta_schedule/database/memory_database.py | 4 +-
.../meta_schedule/database/schedule_fn_database.py | 4 +-
.../feature_extractor/feature_extractor.py | 10 +-
.../feature_extractor/random_feature_extractor.py | 6 +-
python/tvm/meta_schedule/relax_integration.py | 30 +-
python/tvm/meta_schedule/runner/utils.py | 7 +-
python/tvm/meta_schedule/testing/tune_utils.py | 6 +-
.../tvm/meta_schedule/testing/validate_database.py | 50 ++--
python/tvm/meta_schedule/tune.py | 4 +-
python/tvm/relax/base_py_module.py | 32 +--
python/tvm/relax/exec_builder.py | 4 +-
python/tvm/relax/expr.py | 24 +-
python/tvm/relax/frontend/common.py | 10 +-
python/tvm/relax/frontend/nn/core.py | 30 +-
python/tvm/relax/frontend/nn/modules.py | 2 +-
python/tvm/relax/frontend/nn/torch.py | 8 +-
python/tvm/relax/frontend/onnx/onnx_frontend.py | 4 +-
python/tvm/relax/frontend/torch/dynamo.py | 10 +-
.../frontend/torch/exported_program_translator.py | 4 +-
python/tvm/relax/frontend/torch/fx_translator.py | 2 +-
python/tvm/relax/op/base.py | 14 +-
python/tvm/relax/op/memory/view.py | 2 +-
python/tvm/relax/op/set.py | 12 +-
python/tvm/relax/pipeline.py | 2 +-
python/tvm/relax/testing/lib_comparator.py | 8 +-
python/tvm/relax/testing/nn.py | 4 +-
python/tvm/relax/testing/vm.py | 12 +-
python/tvm/relax/training/optimizer.py | 16 +-
python/tvm/relax/training/trainer.py | 90 +++---
python/tvm/relax/transform/transform.py | 16 +-
python/tvm/rpc/client.py | 6 +-
python/tvm/rpc/testing.py | 6 +-
python/tvm/runtime/__init__.py | 6 +-
python/tvm/runtime/{ndarray.py => _tensor.py} | 46 ++--
python/tvm/runtime/disco/session.py | 62 ++---
python/tvm/runtime/executable.py | 2 +-
python/tvm/runtime/params.py | 20 +-
python/tvm/runtime/vm.py | 16 +-
.../tvm/script/ir_builder/relax/distributed/ir.py | 12 +-
python/tvm/script/ir_builder/relax/ir.py | 2 +-
python/tvm/script/ir_builder/tir/ir.py | 4 +-
python/tvm/target/detect_target.py | 3 +-
python/tvm/te/operation.py | 2 +-
python/tvm/testing/runner.py | 22 +-
python/tvm/testing/utils.py | 2 +-
python/tvm/tir/build.py | 3 +-
python/tvm/tir/function.py | 16 +-
python/tvm/tir/op.py | 6 +-
python/tvm/tir/stmt.py | 10 +-
python/tvm/tir/transform/transform.py | 18 +-
python/tvm/topi/sort.py | 4 +-
python/tvm/topi/transform.py | 4 +-
src/contrib/msc/core/ir/graph_builder.cc | 6 +-
src/contrib/msc/core/ir/graph_builder.h | 8 +-
.../msc/core/transform/bind_named_params.cc | 2 +-
src/contrib/msc/core/transform/rewrite_utils.cc | 2 +-
src/contrib/msc/core/utils.h | 2 +-
src/contrib/msc/framework/tensorflow/codegen.cc | 4 +-
src/meta_schedule/arg_info.cc | 2 +-
src/meta_schedule/builder/builder.cc | 4 +-
.../feature_extractor/feature_extractor.cc | 2 +-
.../feature_extractor/per_store_feature.cc | 20 +-
src/meta_schedule/module_equality.cc | 22 +-
src/meta_schedule/module_equality.h | 4 +-
src/node/structural_hash.cc | 6 +-
src/relax/backend/contrib/codegen_c/codegen_c.h | 12 +-
.../backend/contrib/codegen_json/codegen_json.h | 2 +-
src/relax/backend/vm/codegen_vm.cc | 10 +-
src/relax/ir/block_builder.cc | 4 +-
src/relax/ir/expr.cc | 4 +-
src/relax/op/memory/view.cc | 2 +-
src/relax/transform/bind_params.cc | 2 +-
src/relax/transform/fold_constant.cc | 18 +-
src/relax/transform/meta_schedule.cc | 8 +-
src/relax/transform/run_codegen.cc | 2 +-
src/relax/transform/utils.h | 2 +-
src/runtime/const_loader_module.cc | 54 ++--
src/runtime/const_loader_module.h | 6 +-
src/runtime/contrib/arm_compute_lib/acl_runtime.cc | 4 +-
src/runtime/contrib/bnns/bnns_json_runtime.cc | 6 +-
src/runtime/contrib/bnns/bnns_wrp.h | 16 +-
src/runtime/contrib/clml/clml_runtime.cc | 14 +-
src/runtime/contrib/clml/clml_runtime.h | 6 +-
src/runtime/contrib/coreml/coreml_runtime.h | 8 +-
src/runtime/contrib/coreml/coreml_runtime.mm | 17 +-
src/runtime/contrib/cublas/cublas_json_runtime.cc | 8 +-
src/runtime/contrib/cudnn/cudnn_json_runtime.cc | 4 +-
src/runtime/contrib/cutlass/fp16_group_gemm.cuh | 6 +-
.../contrib/cutlass/fp16_group_gemm_sm100.cu | 6 +-
.../contrib/cutlass/fp16_group_gemm_sm90.cu | 6 +-
src/runtime/contrib/cutlass/fp8_gemm.cu | 5 +-
src/runtime/contrib/cutlass/fp8_group_gemm_sm90.cu | 6 +-
.../contrib/cutlass/fp8_groupwise_scaled_gemm.cuh | 14 +-
.../fp8_groupwise_scaled_gemm_runner_sm100.cuh | 2 +-
.../fp8_groupwise_scaled_gemm_runner_sm90.cuh | 2 +-
.../cutlass/fp8_groupwise_scaled_gemm_sm100.cu | 14 +-
.../cutlass/fp8_groupwise_scaled_gemm_sm90.cu | 15 +-
.../fp8_groupwise_scaled_group_gemm_sm100.cu | 8 +-
src/runtime/contrib/cutlass/weight_preprocess.cc | 6 +-
src/runtime/contrib/dnnl/dnnl_json_runtime.cc | 6 +-
.../contrib/hipblas/hipblas_json_runtime.cc | 8 +-
src/runtime/contrib/json/json_runtime.h | 16 +-
src/runtime/contrib/mps/conv.mm | 6 +-
src/runtime/contrib/mps/gemm.mm | 6 +-
src/runtime/contrib/mrvl/mrvl_hw_runtime.cc | 22 +-
src/runtime/contrib/mrvl/mrvl_runtime.cc | 2 +-
src/runtime/contrib/mrvl/mrvl_sw_runtime_lib.cc | 18 +-
src/runtime/contrib/msc/tensorrt_runtime.cc | 22 +-
src/runtime/contrib/mscclpp/allreduce.cu | 2 +-
src/runtime/contrib/nnapi/nnapi_runtime.cc | 6 +-
src/runtime/contrib/nvshmem/memory_allocator.cc | 6 +-
src/runtime/contrib/random/mt_random_engine.cc | 18 +-
src/runtime/contrib/random/random.cc | 2 +-
src/runtime/contrib/rocblas/rocblas.cc | 6 +-
src/runtime/contrib/tensorrt/tensorrt_builder.cc | 6 +-
src/runtime/contrib/tensorrt/tensorrt_builder.h | 2 +-
src/runtime/contrib/tensorrt/tensorrt_runtime.cc | 12 +-
src/runtime/contrib/tflite/tflite_runtime.cc | 6 +-
src/runtime/contrib/tflite/tflite_runtime.h | 14 +-
src/runtime/contrib/vllm/attention_kernels.cu | 2 +-
src/runtime/contrib/vllm/cache_alloc.cc | 18 +-
src/runtime/contrib/vllm/cache_kernels.cu | 29 +-
src/runtime/device_api.cc | 2 +-
src/runtime/disco/bcast_session.cc | 10 +-
src/runtime/disco/bcast_session.h | 8 +-
src/runtime/disco/builtin.cc | 30 +-
src/runtime/disco/disco_worker.cc | 20 +-
src/runtime/disco/distributed/socket_session.cc | 4 +-
src/runtime/disco/loader.cc | 66 ++---
src/runtime/disco/nccl/nccl.cc | 51 ++--
src/runtime/disco/protocol.h | 12 +-
src/runtime/file_utils.cc | 22 +-
src/runtime/file_utils.h | 10 +-
src/runtime/hexagon/hexagon_buffer.h | 2 +-
src/runtime/hexagon/hexagon_device_api.cc | 2 +-
src/runtime/hexagon/hexagon_vtcm_pool.h | 2 +-
src/runtime/memory/memory_manager.cc | 22 +-
src/runtime/meta_data.h | 2 +-
src/runtime/minrpc/rpc_reference.h | 16 +-
src/runtime/opencl/opencl_common.h | 6 +-
src/runtime/opencl/opencl_device_api.cc | 4 +-
src/runtime/profiling.cc | 14 +-
src/runtime/rpc/rpc_endpoint.h | 4 +-
src/runtime/rpc/rpc_local_session.cc | 12 +-
src/runtime/rpc/rpc_module.cc | 34 +--
src/runtime/rpc/rpc_session.h | 12 +-
src/runtime/{ndarray.cc => tensor.cc} | 68 +++--
src/runtime/vm/attn_backend.h | 190 +++++++------
src/runtime/vm/attn_utils.h | 303 ++++++++++-----------
src/runtime/vm/builtin.cc | 35 ++-
src/runtime/vm/executable.cc | 14 +-
src/runtime/vm/hexagon/builtin.cc | 9 +-
src/runtime/vm/kv_state.cc | 20 +-
src/runtime/vm/kv_state.h | 34 +--
src/runtime/vm/lm_support.cc | 53 ++--
src/runtime/vm/paged_kv_cache.cc | 238 ++++++++--------
src/runtime/vm/rnn_state.cc | 72 ++---
...ay_cache_support.cc => tensor_cache_support.cc} | 123 ++++-----
src/runtime/vm/vm.cc | 26 +-
src/script/ir_builder/tir/ir.cc | 4 +-
src/script/printer/relax/expr.cc | 2 +-
src/script/printer/tir/stmt.cc | 24 +-
src/support/scalars.cc | 18 +-
src/support/scalars.h | 16 +-
src/target/codegen.cc | 4 +-
src/target/llvm/codegen_cpu.cc | 8 +-
src/target/llvm/codegen_llvm.cc | 2 +-
src/target/llvm/codegen_params.cc | 2 +-
src/target/llvm/codegen_params.h | 10 +-
src/target/llvm/llvm_module.cc | 6 +-
src/target/source/codegen_c.cc | 6 +-
src/target/source/codegen_c.h | 2 +
src/target/source/codegen_c_host.cc | 8 +-
src/target/source/codegen_c_host.h | 3 +
src/target/source/codegen_params.cc | 4 +-
src/target/source/codegen_params.h | 10 +-
src/target/source/codegen_source_base.h | 2 +-
src/target/source/source_module.cc | 2 +-
src/te/operation/create_primfunc.cc | 4 +-
src/te/operation/create_primfunc.h | 4 +-
src/tir/ir/index_map.cc | 8 +-
src/tir/ir/stmt.cc | 6 +-
src/tir/transforms/bind_params.cc | 10 +-
src/tir/transforms/extract_constants.cc | 6 +-
src/tir/transforms/ir_utils.h | 2 +-
src/tir/transforms/make_packed_api.cc | 22 +-
.../remove_weight_layout_rewrite_block.cc | 32 +--
src/topi/transform.cc | 10 +-
tests/cpp-runtime/opencl/opencl_nativeptr.cc | 6 +-
tests/cpp-runtime/opencl/texture_copy_test.cc | 38 +--
tests/cpp/ndarray_test.cc | 18 +-
tests/cpp/support/scalars_test.cc | 14 +-
.../test_minimal_target_codegen_llvm.py | 6 +-
.../test_runtime_ndarray.py | 10 +-
.../test_runtime_packed_func.py | 6 +-
tests/python/codegen/test_gpu_codegen_allreduce.py | 8 +-
tests/python/codegen/test_inject_ptx_ldg32.py | 4 +-
tests/python/codegen/test_target_codegen_blob.py | 4 +-
tests/python/codegen/test_target_codegen_bool.py | 6 +-
tests/python/codegen/test_target_codegen_c_host.py | 32 +--
.../codegen/test_target_codegen_cross_llvm.py | 6 +-
tests/python/codegen/test_target_codegen_cuda.py | 80 +++---
.../python/codegen/test_target_codegen_cuda_fp4.py | 6 +-
.../python/codegen/test_target_codegen_cuda_fp8.py | 48 ++--
tests/python/codegen/test_target_codegen_device.py | 10 +-
tests/python/codegen/test_target_codegen_extern.py | 12 +-
.../codegen/test_target_codegen_gpu_common.py | 4 +-
tests/python/codegen/test_target_codegen_llvm.py | 87 +++---
tests/python/codegen/test_target_codegen_metal.py | 22 +-
tests/python/codegen/test_target_codegen_opencl.py | 18 +-
tests/python/codegen/test_target_codegen_rocm.py | 16 +-
.../codegen/test_target_codegen_static_init.py | 4 +-
tests/python/codegen/test_target_codegen_vulkan.py | 46 ++--
tests/python/contrib/test_cblas.py | 30 +-
tests/python/contrib/test_coreml_runtime.py | 2 +-
tests/python/contrib/test_cutlass_gemm.py | 42 +--
tests/python/contrib/test_dlpack.py | 8 +-
tests/python/contrib/test_edgetpu_runtime.py | 2 +-
tests/python/contrib/test_hexagon/README_RPC.md | 12 +-
.../python/contrib/test_hexagon/infrastructure.py | 4 +-
tests/python/contrib/test_hexagon/pytest_util.py | 2 +-
.../test_hexagon/test_async_dma_pipeline.py | 16 +-
.../test_hexagon/test_benchmark_elemwise_add.py | 6 +-
.../contrib/test_hexagon/test_dma_builtin.py | 4 +-
.../contrib/test_hexagon/test_meta_schedule.py | 6 +-
.../contrib/test_hexagon/test_parallel_hvx.py | 10 +-
.../test_hexagon/test_parallel_hvx_load_vtcm.py | 28 +-
.../contrib/test_hexagon/test_parallel_scalar.py | 12 +-
.../test_relax_2d_buffer_allocation.py | 2 +-
.../contrib/test_hexagon/test_relax_integration.py | 8 +-
.../test_hexagon/test_software_pipeline_async.py | 6 +-
tests/python/contrib/test_hexagon/test_take.py | 2 +-
.../contrib/test_hexagon/test_thread_pool.py | 6 +-
.../contrib/test_hexagon/test_vtcm_bandwidth.py | 12 +-
tests/python/contrib/test_hipblas.py | 16 +-
tests/python/contrib/test_mps.py | 12 +-
tests/python/contrib/test_msc/test_plugin.py | 4 +-
.../contrib/test_msc/test_translate_relax.py | 2 +-
.../contrib/test_msc/test_translate_tensorrt.py | 4 +-
tests/python/contrib/test_random.py | 12 +-
tests/python/contrib/test_rocblas.py | 12 +-
tests/python/contrib/test_sort.py | 12 +-
tests/python/contrib/test_tflite_runtime.py | 4 +-
.../python/contrib/test_tir_triton_integration.py | 4 +-
tests/python/contrib/test_tvmjs.py | 4 +-
tests/python/disco/test_callback.py | 4 +-
tests/python/disco/test_ccl.py | 20 +-
tests/python/disco/test_loader.py | 23 +-
tests/python/disco/test_session.py | 8 +-
tests/python/driver/test_compile.py | 14 +-
tests/python/ir/test_datatype_nv_fp4.py | 2 +-
tests/python/ir/test_datatype_nv_fp8.py | 4 +-
tests/python/ir/test_ir_container.py | 6 +-
tests/python/ir/test_node_reflection.py | 12 +-
.../meta_schedule/test_meta_schedule_database.py | 4 +-
.../test_meta_schedule_feature_extractor.py | 4 +-
.../test_nnapi/test_from_exported_to_cuda.py | 4 +-
tests/python/nightly/test_nnapi/test_network.py | 2 +-
tests/python/nightly/test_nnapi/test_ops.py | 6 +-
tests/python/relax/backend/clml/utils.py | 2 +-
.../test_runtime_builtin_kv_cache_transfer.py | 14 +-
...est_runtime_builtin_kv_cache_transfer_kernel.py | 16 +-
.../relax/test_backend_dispatch_sort_scan.py | 2 +-
tests/python/relax/test_codegen_coreml.py | 42 +--
tests/python/relax/test_codegen_cublas.py | 2 +-
tests/python/relax/test_codegen_cudnn.py | 2 +-
tests/python/relax/test_codegen_cutlass.py | 20 +-
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_contrib_vllm.py | 16 +-
tests/python/relax/test_dataflow_inplace.py | 8 +-
tests/python/relax/test_dlpack_integration.py | 76 +++---
tests/python/relax/test_e2e_op_dynamic.py | 16 +-
tests/python/relax/test_frontend_common.py | 2 +-
tests/python/relax/test_frontend_dynamo.py | 2 +-
.../relax/test_frontend_from_exported_program.py | 8 +-
tests/python/relax/test_frontend_from_fx.py | 8 +-
tests/python/relax/test_frontend_nn_debug.py | 4 +-
.../python/relax/test_frontend_nn_extern_module.py | 8 +-
tests/python/relax/test_frontend_nn_op.py | 32 ++-
tests/python/relax/test_frontend_onnx.py | 4 +-
tests/python/relax/test_frontend_stablehlo.py | 6 +-
.../relax/test_meta_schedule_relax_integration.py | 6 +-
tests/python/relax/test_op_datatype.py | 6 +-
tests/python/relax/test_op_gradient_numeric.py | 8 +-
tests/python/relax/test_op_inspect.py | 20 +-
tests/python/relax/test_op_misc.py | 2 +-
tests/python/relax/test_op_take.py | 16 +-
tests/python/relax/test_op_view.py | 22 +-
tests/python/relax/test_pipeline.py | 8 +-
tests/python/relax/test_pytorch_integration.py | 2 +-
tests/python/relax/test_relax_operators.py | 69 ++---
tests/python/relax/test_runtime_builtin.py | 42 +--
...runtime_builtin_paged_attention_kv_cache_cpu.py | 12 +-
..._builtin_paged_attention_kv_cache_flashinfer.py | 14 +-
...ltin_paged_attention_kv_cache_mla_flashinfer.py | 26 +-
...ime_builtin_paged_attention_kv_cache_mla_tir.py | 26 +-
...runtime_builtin_paged_attention_kv_cache_tir.py | 14 +-
.../python/relax/test_runtime_builtin_rnn_state.py | 23 +-
.../relax/test_runtime_sampling_flashinfer.py | 4 +-
tests/python/relax/test_tir_call_source_kernel.py | 4 +-
.../relax/test_training_optimizer_numeric.py | 2 +-
tests/python/relax/test_transform_bind_params.py | 12 +-
tests/python/relax/test_transform_codegen_pass.py | 4 +-
tests/python/relax/test_transform_cse.py | 8 +-
.../python/relax/test_transform_few_shot_tuning.py | 4 +-
.../test_transform_fold_batch_norm_to_conv2d.py | 22 +-
tests/python/relax/test_transform_fold_constant.py | 8 +-
.../relax/test_transform_gradient_numeric.py | 12 +-
.../relax/test_transform_lazy_transform_params.py | 2 +-
.../relax/test_transform_to_mixed_precision.py | 6 +-
.../relax/test_vm_alloc_storage_with_scope.py | 2 +-
tests/python/relax/test_vm_build.py | 134 ++++-----
tests/python/relax/test_vm_builtin.py | 4 +-
tests/python/relax/test_vm_callback_function.py | 4 +-
tests/python/relax/test_vm_codegen_only.py | 28 +-
tests/python/relax/test_vm_cuda_graph.py | 6 +-
tests/python/relax/test_vm_execbuilder.py | 34 +--
tests/python/relax/test_vm_instrument.py | 4 +-
tests/python/relax/test_vm_multi_device.py | 20 +-
tests/python/relax/test_vm_profiler.py | 4 +-
.../python/runtime/test_evaluator_with_preproc.py | 6 +-
tests/python/runtime/test_executable.py | 40 +--
tests/python/runtime/test_runtime_container.py | 2 +-
tests/python/runtime/test_runtime_dlpack.py | 8 +-
tests/python/runtime/test_runtime_extension.py | 2 +-
tests/python/runtime/test_runtime_measure.py | 2 +-
tests/python/runtime/test_runtime_module_load.py | 22 +-
tests/python/runtime/test_runtime_nd_array.py | 56 ++--
tests/python/runtime/test_runtime_rpc.py | 32 +--
tests/python/runtime/test_runtime_trace.py | 44 +--
tests/python/target/test_arm_target.py | 12 +-
tests/python/te/test_te_create_primfunc.py | 8 +-
tests/python/tir-base/test_tir_imm_values.py | 2 +-
tests/python/tir-base/test_tir_index_map.py | 12 +-
tests/python/tir-base/test_tir_intrin.py | 28 +-
tests/python/tir-base/test_tir_ptx_cp_async.py | 12 +-
tests/python/tir-base/test_tir_ptx_ldmatrix.py | 4 +-
tests/python/tir-base/test_tir_ptx_mma.py | 102 +++----
tests/python/tir-base/test_tir_ptx_mma_sp.py | 16 +-
.../tir-base/test_tir_structural_equal_hash.py | 10 +-
.../python/tir-base/test_tir_te_extern_primfunc.py | 30 +-
.../test_tir_schedule_decompose_padding.py | 6 +-
.../test_tir_schedule_rolling_buffer.py | 6 +-
..._tir_schedule_tensorize_ldmatrix_mma_numeric.py | 6 +-
.../test_tir_schedule_tensorize_mfma_numeric.py | 6 +-
.../test_tir_transform_inject_ptx_async_copy.py | 14 +-
.../test_tir_transform_inject_software_pipeline.py | 6 +-
.../test_tir_transform_lower_intrin.py | 6 +-
.../test_tir_transform_lower_tvm_builtin.py | 2 +-
.../test_tir_transform_make_packed_api.py | 11 +-
.../tvmscript/test_tvmscript_ir_builder_tir.py | 4 +-
tests/python/tvmscript/test_tvmscript_ops.py | 14 +-
web/.gitignore | 2 +-
web/apps/browser/rpc_server.html | 16 +-
web/emcc/wasm_runtime.cc | 28 +-
web/src/artifact_cache.ts | 28 +-
web/src/ctypes.ts | 4 +-
web/src/index.ts | 6 +-
web/src/rpc_server.ts | 24 +-
web/src/runtime.ts | 198 +++++++-------
web/tests/node/test_packed_func.js | 2 +-
web/tests/node/{test_ndarray.js => test_tensor.js} | 0
web/tests/python/relax_rpc_test.py | 4 +-
web/tests/python/webgpu_rpc_test.py | 4 +-
506 files changed, 4061 insertions(+), 3861 deletions(-)
delete mode 100644 docs/reference/api/python/runtime/ndarray.rst
rename ffi/include/tvm/ffi/container/{ndarray.h => tensor.h} (68%)
rename ffi/python/tvm_ffi/cython/{ndarray.pxi => tensor.pxi} (89%)
rename ffi/python/tvm_ffi/{ndarray.py => tensor.py} (98%)
rename ffi/src/ffi/{ndarray.cc => tensor.cc} (71%)
rename ffi/tests/cpp/{test_ndarray.cc => test_tensor.cc} (63%)
rename ffi/tests/python/{test_ndarray.py => test_tensor.py} (93%)
rename include/tvm/runtime/{ndarray.h => tensor.h} (78%)
rename include/tvm/runtime/vm/{ndarray_cache_support.h =>
tensor_cache_support.h} (68%)
rename jvm/core/src/main/java/org/apache/tvm/{NDArray.java => Tensor.java}
(90%)
rename jvm/core/src/main/java/org/apache/tvm/{NDArrayBase.java =>
TensorBase.java} (86%)
delete mode 100644 jvm/core/src/test/java/org/apache/tvm/NDArrayTest.java
create mode 100644 jvm/core/src/test/java/org/apache/tvm/TensorTest.java
rename python/tvm/runtime/{ndarray.py => _tensor.py} (90%)
rename src/runtime/{ndarray.cc => tensor.cc} (74%)
rename src/runtime/vm/{ndarray_cache_support.cc => tensor_cache_support.cc}
(74%)
rename web/tests/node/{test_ndarray.js => test_tensor.js} (100%)
