MCPcopy Create free account

hub / github.com/alibaba/BladeDISC / functions

Functions6,088 in github.com/alibaba/BladeDISC

↓ 6 callersFunctionisGpuMhlo
tao_compiler/mlir/disc/transforms/placement_utils.cc:24
↓ 6 callersFunctionisMhloOrStdOnTensor
tao_compiler/mlir/disc/transforms/placement_utils.h:87
↓ 6 callersMethodisValid
tao_compiler/mlir/disc/transforms/shape_utils.h:108
↓ 6 callersFunctionmakeMatrixDescriptor
tao_compiler/mlir/xla/ral/context/stream_executor_based_impl.cc:115
↓ 6 callersMethodset_g
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/tensor.hpp:412
↓ 6 callersMethodset_mode
(self, *, observe: bool, fake_quant: bool)
tools/torch_quant/torch_quant/observer.py:168
↓ 6 callersMethodsoftmax
(x)
pytorch_blade/tests/disc/ops/test_nn_ops.py:88
↓ 6 callersMethodsyncOnStream
tao_compiler/mlir/xla/ral/device/gpu/gpu_driver.cc:219
↓ 6 callersFunctionto_string
pytorch_blade/pytorch_blade/ltc/include/torch/csrc/lazy/ts_backend/ts_lowering_context.h:72
↓ 6 callersFunctiontorch_version_number
()
pytorch_blade/torch_blade/utils.py:227
↓ 6 callersFunctiontry_import_from_platform_alibaba
(module_name, disc_root=None)
scripts/python/common_setup.py:553
↓ 6 callersFunctiontry_import_from_platform_alibaba
(module_name, disc_root=None)
pytorch_blade/common_setup.py:553
↓ 5 callersFunctionAsciiStrToLower
pytorch_blade/pytorch_blade/common_utils/utils.cpp:43
↓ 5 callersMethodCanContractEdge
tao/tao_bridge/tf/graphcycles.cc:360
↓ 5 callersMethodCommunicate
tao/tao_bridge/tf/subprocess.cc:301
↓ 5 callersFunctionGetBatchSize
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:829
↓ 5 callersMethodGetCondId
tao/tao_bridge/passes/functionalize_cond.cc:194
↓ 5 callersFunctionIncomingEdgeAsOutput
tao/tao_bridge/passes/tao_build_tao_op_pass.cc:51
↓ 5 callersMethodInsertEdge
tao/tao_bridge/tf/graphcycles.cc:167
↓ 5 callersFunctionInsertTranspose
tao_compiler/mlir/disc/transforms/disc_dense_to_sparse.cc:127
↓ 5 callersMethodLookupAncestorId
tao/tao_bridge/passes/functionalize_cond.cc:206
↓ 5 callersMethodMakeSymbolPredicate
tao/tao_bridge/tf/deadness_analysis.cc:418
↓ 5 callersFunctionQuantizedTypeToIntegerType
tao_compiler/mlir/disc/transforms/lower_tf.cc:228
↓ 5 callersMethodRun
tao/tao_bridge/passes/tao_defuse_pass.cc:267
↓ 5 callersMethodRun
pytorch_blade/pytorch_blade/ltc/disc_compiler/disc_compiler.cpp:41
↓ 5 callersFunctionRunTest
tensorflow_blade/src/util/tf_allocator_util_test.cc:18
↓ 5 callersMethod_ScriptFunction2Module
(self, nn_module)
pytorch_blade/tests/disc/testing_base.py:70
↓ 5 callersMethod__init__
(self, dtype: torch.dtype, qscheme: torch.qscheme, ch_axis: int = -1, **kwargs)
tools/torch_quant/torch_quant/observer.py:103
↓ 5 callersMethod__init__
( self, in_dim: int, out_dim: int, bias: bool = True, init: str = "def
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/ops.py:92
↓ 5 callersMethod__init__
(self, dim = 0, world_size = 1)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/optimization/distributed/utils.py:22
↓ 5 callersMethod__init__
(self)
pytorch_blade/tests/tensorrt/test_optimize.py:29
↓ 5 callersMethod__init__
(self)
pytorch_blade/tests/disc/pdl/test_e2e/test_quantization.py:360
↓ 5 callersMethod_add_unsupported
(self, node)
pytorch_blade/torch_blade/onnx_backends/backend_testbed.py:350
↓ 5 callersMethod_check_is_leaf_module
( self, name: str, module: torch.nn.Module, graph: torch.fx.Graph )
tools/torch_quant/tests/test_module_fx_trace.py:67
↓ 5 callersMethod_make_check
(self, graph, target)
pytorch_blade/tests/tensorrt/test_support_info.py:434
↓ 5 callersMethod_test_binary_ops
(self, binary_ops_func, test_int=True)
pytorch_blade/tests/disc/ops/test_binary_ops.py:45
↓ 5 callersMethod_test_replace_aten_fake_quant
(self, model, inp, all_target_val)
pytorch_blade/tests/quantization/test_graph_process.py:89
↓ 5 callersMethod_test_scalar_func
(self, torch_func)
pytorch_blade/tests/disc/ops/test_binary_ops.py:99
↓ 5 callersFunction_update_list_container
(container_map, local, graph, node, val, container)
pytorch_blade/torch_blade/python_ir_analysis.py:26
↓ 5 callersMethodadd_edge
(self, src: int, dst: int)
pytorch_blade/torch_blade/algorithm/directed_graph.py:48
↓ 5 callersMethodadd_node
(self, node: int)
pytorch_blade/torch_blade/algorithm/directed_graph.py:26
↓ 5 callersMethodassign
tao_compiler/mlir/xla/ral/context/custom_library/tf_topk.cu.h:114
↓ 5 callersFunctionbuildLowerVectors
tao_compiler/mlir/disc/transforms/disc_transform_schedule.cc:233
↓ 5 callersFunctionbuildSplitHandlesOp
tao_compiler/mlir/disc/transforms/disc_transform_schedule.cc:242
↓ 5 callersFunctioncreate_model
(task: Optional[str] = None, id_or_path: Optional[str] = None, preprocessor: Optional[Preproc
examples/PyTorch/Inference/hf_transformers/blade_adapter.py:244
↓ 5 callersMethodcvt_to_disc
(self, nn_module, test_data, annotations=[])
pytorch_blade/tests/disc/testing_base.py:79
↓ 5 callersMethodcycles_graph_node_id
The ID of the cluster as represented in `cycle_detector_`.
tao_compiler/mlir/disc/transforms/lhlo_fusion.cc:196
↓ 5 callersFunctionemitNotToVectorReduction
tao_compiler/mlir/disc/transforms/lhlo_legalize_roots_to_loops.cc:476
↓ 5 callersFunctiongetAtomicRMWKind
TODO: check the definition of "SignlessInteger"
tao_compiler/mlir/disc/transforms/lhlo_elemental_utils.cc:1289
↓ 5 callersMethodgetDim
tao_compiler/mlir/disc/transforms/shape_utils.cc:664
↓ 5 callersMethodget_contexts
(cls)
pytorch_blade/torch_blade/config.py:109
↓ 5 callersMethodget_nelems
Return element number of the param. The number is the meaning values for a tensor, instead of whole buffer. It is the number without counting in paddi
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/tensor.hpp:606
↓ 5 callersMethodget_or_create_module
(self, full_path: str, constructor: Callable[[], nn.Module])
tools/torch_quant/torch_quant/graph.py:181
↓ 5 callersMethodget_simple_conv_net_feed_dict
(self, batch: int = 1)
tensorflow_blade/tests/tf_test_common.py:93
↓ 5 callersMethodgroup_topolist
(self)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:55
↓ 5 callersMethodhasMember
pytorch_blade/pytorch_blade/compiler/jit/torch/schema_set.cpp:26
↓ 5 callersMethodinitialize
Initialize the canonicalizer by building the set of patterns used during execution.
tao_compiler/mlir/disc/transforms/disc_canonicalizer.cc:37
↓ 5 callersFunctioninternal_root_dir
()
pytorch_blade/common_setup.py:534
↓ 5 callersFunctionisBcastOp
tao_compiler/mlir/disc/transforms/fusion_utils_transform_based.cc:50
↓ 5 callersFunctionisDynamic
pytorch_blade/pytorch_blade/ltc/include/torch/csrc/lazy/ts_backend/dynamic_ir.h:60
↓ 5 callersMethodisDynamic
tao_compiler/mlir/disc/transforms/shape_utils.h:34
↓ 5 callersFunctionisIdentityPermutation
tao_compiler/mlir/disc/transforms/disc_transpose_simplifier.cc:92
↓ 5 callersFunctionmakeConvParamsKey
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.h:313
↓ 5 callersFunctionmakeDynamicShapeConvParamsKey
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.h:342
↓ 5 callersMethodname
(self)
tensorflow_blade/tf_blade/gpu/tf_to_trt.py:62
↓ 5 callersFunctionoptimize
(task: Optional[str] = None, id_or_path: Optional[str] = None, model: Optional[PreTrainedModel] =
examples/PyTorch/Inference/hf_transformers/blade_adapter.py:262
↓ 5 callersMethodoutput_nodes
Find nodes in graph segment that output to outside of segment. See the explaination of GraphSegment"s `required_outputs`.
tensorflow_blade/tf_blade/util/simple_graph.py:341
↓ 5 callersMethodoutput_offsets
Used to identity the indices of a certain segment"s outputs. For example, the out_node_names is ["a", "b"] "a" has 2 outputs
tensorflow_blade/tf_blade/util/simple_graph.py:378
↓ 5 callersMethodpermute
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/tensor.hpp:925
↓ 5 callersFunctionpipeline
( task: Optional[str] = None, model: Optional[Union[str, PreTrainedModel]] = None, tokenizer: Opti
examples/PyTorch/Inference/hf_transformers/blade_adapter.py:311
↓ 5 callersFunctionprint_memref_0d
tao_compiler/mlir/xla/ral/context/context_util.h:39
↓ 5 callersMethodquantizable_nodes
(self)
tools/torch_quant/torch_quant/graph.py:132
↓ 5 callersFunctionreadFromBinaryStream
tao_compiler/mlir/xla/ral/ral_metadata.cc:28
↓ 5 callersMethodreplace_module
(self, full_path: str, module: nn.Module)
tools/torch_quant/torch_quant/graph.py:172
↓ 5 callersMethodresource_kind
tao/tao_bridge/tf/resource_operation_table.h:50
↓ 5 callersMethodsetUp
(self)
pytorch_blade/tests/disc/testing_base.py:202
↓ 5 callersFunctionsplit_feat
(feat, ps1, ps2, has_batch=False)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/utils.py:36
↓ 5 callersMethodstep
tao/tao_bridge/tf/deadness_analysis.cc:257
↓ 5 callersFunctionsubmodule_filter
(module_filter: ModuleFilter, module_name: str)
tools/torch_quant/torch_quant/module.py:71
↓ 5 callersFunctionsupported_node_fusion
(graph, block, unsupported_nodes, support_number_ios=False)
pytorch_blade/torch_blade/clustering/support_fusion_group.py:82
↓ 5 callersMethodswap
tao_compiler/mlir/xla/ral/context/custom_library/tf_topk.cu.h:129
↓ 5 callersFunctiontryScalarTypeFromJitType
pytorch_blade/pytorch_blade/compiler/jit/torch/shape_analysis.cpp:588
↓ 5 callersFunctionunifold2foldacc
convert unifold weight to foldacc
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/fold/unifold.py:20
↓ 4 callersMethodAdd
Adds all ResourceOp s in `other` to this set.
tao/tao_bridge/tf/resource_operation_safety_analysis.cc:175
↓ 4 callersFunctionAddNodeDefToGraph
tao/tao_bridge/passes/functionalize_control_flow_util.cc:36
↓ 4 callersFunctionAppendToEnvArgv
Append the string s0[0, .., s0len-1] concatenated with s1[0, .., s1len-1] as a newly allocated nul-terminated string to the array *a. If s0==nullptr,
tao/tao_bridge/tf/parse_flags_from_env.cc:64
↓ 4 callersFunctionCastMemRefTo
tao_compiler/mlir/disc/disc_util.cc:382
↓ 4 callersFunctionCommaSeparatedString
tao/tao_bridge/tf/util.h:331
↓ 4 callersMethodContractEdge
tao/tao_bridge/tf/graphcycles.cc:370
↓ 4 callersMethodDebugString
tao/tao_bridge/tf/graphcycles.cc:449
↓ 4 callersFunctionEdgeIndex
Returns the index of edge (from, to) in *edges or -1 if it is not in *edges.
tao/tao_bridge/tf/graphcycles_test.cc:201
↓ 4 callersFunctionFindNodeByName
tao/tao_bridge/passes/tao_defuse_pass_test.cc:221
↓ 4 callersMethodGetCallNode
tao/tao_bridge/passes/tao_encapsulate_subgraphs_pass.cc:721
↓ 4 callersFunctionGetDeviceStrs
pytorch_blade/pytorch_blade/compiler/mlir/converters/mhlo_conversion.cpp:74
↓ 4 callersFunctionGetFunctionBody
tao/tao_bridge/tf/const_analysis.cc:35
↓ 4 callersMethodGetGraph
tao/tao_bridge/passes/tao_encapsulate_subgraphs_pass.cc:776
↓ 4 callersFunctionGetInputsForNode
tao/tao_bridge/passes/tao_clone_constants_for_better_clustering_test.cc:79
↓ 4 callersFunctionInputEdgeToTensorId
tao/tao_bridge/tf/deadness_analysis.cc:911
↓ 4 callersFunctionIsFunctionalControlFlowOps
tao/tao_bridge/tf/compilability_check_util.cc:91
↓ 4 callersMethodIsMetadataOp
static*/
tao/tao_bridge/tf/xla_op_registry.cc:465
← previousnext →401–500 of 6,088, ranked by callers