1 file changed
+1
-1
lines changed- paddle/fluid/distributed/collective/deep_ep/deep_ep.cpp+51-61
- paddle/fluid/distributed/collective/deep_ep/deep_ep.hpp+3-7
- paddle/fluid/distributed/collective/deep_ep/include/event_pool.h+1-1
- paddle/fluid/distributed/collective/deep_ep/include/types.h+2
- paddle/fluid/distributed/collective/deep_ep/kernels/api.cuh+16-13
- paddle/fluid/distributed/collective/deep_ep/kernels/configs.cuh+7-7
- paddle/fluid/distributed/collective/deep_ep/kernels/ibgda_device.cuh+82-18
- paddle/fluid/distributed/collective/deep_ep/kernels/internode.cu+517-454
- paddle/fluid/distributed/collective/deep_ep/kernels/intranode.cu+305-171
- paddle/fluid/distributed/collective/deep_ep/kernels/launch.cuh+9
- paddle/fluid/distributed/collective/deep_ep/kernels/runtime.cu+17-30
- paddle/fluid/distributed/collective/deep_ep/kernels/utils.cuh+288-45
- paddle/fluid/distributed/collective/deep_ep/src/event_pool.cc+10
- paddle/fluid/eager/auto_code_generator/generator/python_c_gen.py+1-1
- paddle/fluid/framework/executor.cc+1-1
- paddle/fluid/framework/ir/conv_bn_fuse_pass.h+1-1
- paddle/fluid/framework/ir/graph_pattern_detector.cc+34-15
- paddle/fluid/framework/ir/graph_pattern_detector.h+16-2
- paddle/fluid/framework/ir/onednn/matmul_elementwise_add_onednn_fuse_pass.cc+4-4
- paddle/fluid/framework/ir/onednn/matmul_elementwise_add_onednn_fuse_pass.h+3-3
- paddle/fluid/framework/new_executor/instruction/cuda_graph_instruction.cc+2-2
- paddle/fluid/framework/op_kernel_type.h+1-1
- paddle/fluid/pir/transforms/onednn/cpu_bfloat16_type_placement_pass.cc+1-1
- paddle/fluid/pir/transforms/onednn/depthwise_conv_onednn_pass.cc+5-5
- paddle/fluid/pir/transforms/onednn/depthwise_conv_onednn_pass.h+1-1
- paddle/fluid/pybind/pybind.cc+11
- paddle/phi/core/distributed/auto_parallel/dist_attr.cc+4
- paddle/phi/core/distributed/auto_parallel/dist_attr.h+2
- paddle/phi/infermeta/spmd_rules/dim_trans.cc+255-1
- paddle/phi/infermeta/spmd_rules/dim_trans.h+11
- paddle/phi/infermeta/spmd_rules/reshape.cc+19-20
- paddle/phi/kernels/gpu/cum_kernel.cu+83-3
- paddle/phi/kernels/impl/slogdeterminant_grad_kernel_impl.h+48-2
- paddle/phi/ops/yaml/op_compat.yaml+1-1
- python/paddle/__init__.py+12
- python/paddle/amp/__init__.py+9
- python/paddle/amp/auto_cast.py+71
- python/paddle/autograd/__init__.py+3
- python/paddle/base/dygraph/base.py+2
- python/paddle/device/__init__.py+33-1
- python/paddle/distributed/fleet/meta_parallel/dualpipev.py+20-1
- python/paddle/distributed/fleet/meta_parallel/zero_bubble_utils.py+9
- python/paddle/nn/functional/activation.py+23-4
- python/paddle/nn/functional/input.py+2
- python/paddle/nn/layer/activation.py+26-4
- python/paddle/sparse/unary.py+4
- python/paddle/tensor/__init__.py+8
- python/paddle/tensor/creation.py+178-41
- python/paddle/tensor/logic.py+3
- python/paddle/tensor/manipulation.py+8-1
- python/paddle/tensor/math.py+8
- python/paddle/tensor/search.py+32
- python/paddle/tensor/stat.py+2
- python/paddle/utils/decorator_utils.py+39-23
- test/amp/test_get_autocast_dtype.py+77
- test/amp/test_is_autocast_enabled.py+72
- test/auto_parallel/semi_auto_parallel_for_embedding.py+8
- test/cpp/auto_parallel/CMakeLists.txt+3
- test/cpp/auto_parallel/reshape_co_shard_spmd_rule_test.cc+153
- test/cpp/auto_parallel/spmd_rule_test_util.cc+19
- test/cpp/auto_parallel/spmd_rule_test_util.h+10
- test/deprecated/ir/inference/inference_pass_test.py+3-3
- test/deprecated/ir/inference/quant_dequant_test.py+3-3
- test/deprecated/ir/inference/test_trt_inference_predictor_deprecated.py+3-3
- test/ir/inference/test_conv_transpose_bn_fuse_pass.py+3-3
- test/ir/inference/test_conv_transpose_eltwiseadd_bn_fuse_pass.py+3-3
- test/ir/inference/test_mkldnn_depthwise_conv_pass.py+1-1
- test/ir/inference/test_mkldnn_matmul_v2_activation_fuse_pass.py+1-1
- test/ir/inference/test_mkldnn_pad3d_op.py+1-1
- test/ir/inference/test_onednn_batch_norm_act_fuse_pass.py+4-4
- test/ir/inference/test_onednn_multi_gru_seq_fuse_pass.py+3-3
- test/legacy_test/test_argwhere_api.py+187
- test/legacy_test/test_autograd_function.py+679
- test/legacy_test/test_creation.py+307
- test/legacy_test/test_empty_like_op.py+77-64
- test/legacy_test/test_fill_any_like_op.py+1-1
- test/legacy_test/test_full_like_op.py+1-1
- test/legacy_test/test_fusion_lstm_op.py+1-1
- test/legacy_test/test_gelu_op.py+123-29
- test/legacy_test/test_inplace.py+16
- test/legacy_test/test_mul.py+138
- test/legacy_test/test_pow.py+53
- test/legacy_test/test_prod_op.py+113
- test/legacy_test/test_ravel_op.py+237
- test/legacy_test/test_reshape_op.py+114
- test/legacy_test/test_unique_consecutive_op.py+30
- test/legacy_test/test_zero_dim_no_backward_api.py+12
- test/xpu/test_zero_dim_tensor_xpu.py+12
0 commit comments