Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Paddle
Submodule Paddle updated 88 files
+51 −61 paddle/fluid/distributed/collective/deep_ep/deep_ep.cpp
+3 −7 paddle/fluid/distributed/collective/deep_ep/deep_ep.hpp
+1 −1 paddle/fluid/distributed/collective/deep_ep/include/event_pool.h
+2 −0 paddle/fluid/distributed/collective/deep_ep/include/types.h
+16 −13 paddle/fluid/distributed/collective/deep_ep/kernels/api.cuh
+7 −7 paddle/fluid/distributed/collective/deep_ep/kernels/configs.cuh
+82 −18 paddle/fluid/distributed/collective/deep_ep/kernels/ibgda_device.cuh
+517 −454 paddle/fluid/distributed/collective/deep_ep/kernels/internode.cu
+305 −171 paddle/fluid/distributed/collective/deep_ep/kernels/intranode.cu
+9 −0 paddle/fluid/distributed/collective/deep_ep/kernels/launch.cuh
+17 −30 paddle/fluid/distributed/collective/deep_ep/kernels/runtime.cu
+288 −45 paddle/fluid/distributed/collective/deep_ep/kernels/utils.cuh
+10 −0 paddle/fluid/distributed/collective/deep_ep/src/event_pool.cc
+1 −1 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
+34 −15 paddle/fluid/framework/ir/graph_pattern_detector.cc
+16 −2 paddle/fluid/framework/ir/graph_pattern_detector.h
+4 −4 paddle/fluid/framework/ir/onednn/matmul_elementwise_add_onednn_fuse_pass.cc
+3 −3 paddle/fluid/framework/ir/onednn/matmul_elementwise_add_onednn_fuse_pass.h
+2 −2 paddle/fluid/framework/new_executor/instruction/cuda_graph_instruction.cc
+1 −1 paddle/fluid/framework/op_kernel_type.h
+1 −1 paddle/fluid/pir/transforms/onednn/cpu_bfloat16_type_placement_pass.cc
+5 −5 paddle/fluid/pir/transforms/onednn/depthwise_conv_onednn_pass.cc
+1 −1 paddle/fluid/pir/transforms/onednn/depthwise_conv_onednn_pass.h
+11 −0 paddle/fluid/pybind/pybind.cc
+4 −0 paddle/phi/core/distributed/auto_parallel/dist_attr.cc
+2 −0 paddle/phi/core/distributed/auto_parallel/dist_attr.h
+255 −1 paddle/phi/infermeta/spmd_rules/dim_trans.cc
+11 −0 paddle/phi/infermeta/spmd_rules/dim_trans.h
+19 −20 paddle/phi/infermeta/spmd_rules/reshape.cc
+83 −3 paddle/phi/kernels/gpu/cum_kernel.cu
+48 −2 paddle/phi/kernels/impl/slogdeterminant_grad_kernel_impl.h
+1 −1 paddle/phi/ops/yaml/op_compat.yaml
+12 −0 python/paddle/__init__.py
+9 −0 python/paddle/amp/__init__.py
+71 −0 python/paddle/amp/auto_cast.py
+3 −0 python/paddle/autograd/__init__.py
+2 −0 python/paddle/base/dygraph/base.py
+33 −1 python/paddle/device/__init__.py
+20 −1 python/paddle/distributed/fleet/meta_parallel/dualpipev.py
+9 −0 python/paddle/distributed/fleet/meta_parallel/zero_bubble_utils.py
+23 −4 python/paddle/nn/functional/activation.py
+2 −0 python/paddle/nn/functional/input.py
+26 −4 python/paddle/nn/layer/activation.py
+4 −0 python/paddle/sparse/unary.py
+8 −0 python/paddle/tensor/__init__.py
+178 −41 python/paddle/tensor/creation.py
+3 −0 python/paddle/tensor/logic.py
+8 −1 python/paddle/tensor/manipulation.py
+8 −0 python/paddle/tensor/math.py
+32 −0 python/paddle/tensor/search.py
+2 −0 python/paddle/tensor/stat.py
+39 −23 python/paddle/utils/decorator_utils.py
+77 −0 test/amp/test_get_autocast_dtype.py
+72 −0 test/amp/test_is_autocast_enabled.py
+8 −0 test/auto_parallel/semi_auto_parallel_for_embedding.py
+3 −0 test/cpp/auto_parallel/CMakeLists.txt
+153 −0 test/cpp/auto_parallel/reshape_co_shard_spmd_rule_test.cc
+19 −0 test/cpp/auto_parallel/spmd_rule_test_util.cc
+10 −0 test/cpp/auto_parallel/spmd_rule_test_util.h
+3 −3 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
+1 −1 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
+4 −4 test/ir/inference/test_onednn_batch_norm_act_fuse_pass.py
+3 −3 test/ir/inference/test_onednn_multi_gru_seq_fuse_pass.py
+187 −0 test/legacy_test/test_argwhere_api.py
+679 −0 test/legacy_test/test_autograd_function.py
+307 −0 test/legacy_test/test_creation.py
+77 −64 test/legacy_test/test_empty_like_op.py
+1 −1 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
+123 −29 test/legacy_test/test_gelu_op.py
+16 −0 test/legacy_test/test_inplace.py
+138 −0 test/legacy_test/test_mul.py
+53 −0 test/legacy_test/test_pow.py
+113 −0 test/legacy_test/test_prod_op.py
+237 −0 test/legacy_test/test_ravel_op.py
+114 −0 test/legacy_test/test_reshape_op.py
+30 −0 test/legacy_test/test_unique_consecutive_op.py
+12 −0 test/legacy_test/test_zero_dim_no_backward_api.py
+12 −0 test/xpu/test_zero_dim_tensor_xpu.py