Functions — github.com/InfiniTensor/InfiniTensor

CodeHub MCPcopy Create free account

hub / github.com/InfiniTensor/InfiniTensor / functions

Functions2,429 in github.com/InfiniTensor/InfiniTensor

⨍ Functions 2,429◇ Types & classes 632

↓ 2 callersMethodgetConstant

src/nnet/Visitor/SimplifyExprVisitor.cc:47

↓ 2 callersMethodgetDType

include/operators/rope.h:22

↓ 2 callersMethodgetDims

include/core/tensor.h:36

↓ 2 callersMethodgetExprRange

src/nnet/Visitor/SimplifyExprVisitor.cc:17

↓ 2 callersMethodgetExprStride

include/nnet/Visitor/StrideVisitor.h:31

↓ 2 callersMethodgetFlops

src/nnet/expr.cc:417

↓ 2 callersMethodgetFuncType

include/nnet/expr.h:383

↓ 2 callersMethodgetInputSize

src/nnet/expr.cc:427

↓ 2 callersMethodgetInputs

* @brief Gets input tensors of this graph. */

include/core/graph.h:101

↓ 2 callersMethodgetModDivExpr

src/nnet/expr.cc:223

↓ 2 callersMethodgetModDivParameter

src/nnet/expr.cc:207

↓ 2 callersMethodgetMomentum

include/operators/batch_norm.h:43

↓ 2 callersMethodgetNCDHWFQRS

include/operators/conv.h:177

↓ 2 callersMethodgetNearestMode

include/operators/resize.h:124

↓ 2 callersMethodgetNum

include/operators/extend.h:32

↓ 2 callersMethodgetNumTensors

include/nnet/iterator_table.h:85

↓ 2 callersMethodgetObjectRangesWithPaddings

src/nnet/expr.cc:182

↓ 2 callersMethodgetOffsetCur

src/nnet/Visitor/PatternMatcher.cc:16

↓ 2 callersMethodgetOutputPadding

include/operators/conv.h:230

↓ 2 callersMethodgetOutputRanges

src/nnet/expr.cc:449

↓ 2 callersMethodgetRangeOp

src/nnet/iterator_table.cc:365

↓ 2 callersFunctiongetResourceFilePath

src/nnet/test.cc:23

↓ 2 callersMethodgetSearchState

src/nnet/derivator.cc:460

↓ 2 callersMethodgetShape

(self, name: str)

pyinfinitensor/src/pyinfinitensor/onnx.py:1497

↓ 2 callersMethodgetSize

include/core/data_type.h:67

↓ 2 callersMethodgetStrides

src/nnet/Visitor/SimplifyExprVisitor.cc:43

↓ 2 callersMethodgetStridesConstant

src/nnet/Visitor/SimplifyExprVisitor.cc:6

↓ 2 callersMethodgetTables

vector<Tensor> tensorMap_r( pattern.nInputs); // [pattern tensor ID] -> real tensor map<string, VarRangePair> iterToRange_r; // [pattern iter] -> iter

include/nnet/iterator_table.h:92

↓ 2 callersMethodgetWorkspaceSize

include/core/workspace.h:22

↓ 2 callersMethodhasMatched

include/core/graph_match.h:51

↓ 2 callersMethodhash

include/nnet/expr.h:135

↓ 2 callersFunctioninferCastType

src/core/graph_handler.cc:696

↓ 2 callersMethodinfo

src/core/lazy_allocator.cc:211

↓ 2 callersFunctioninitGatherMetaData

include/cuda/gather.h:32

↓ 2 callersMethodisCuda

include/core/runtime.h:75

↓ 2 callersMethodisOthers

include/core/tensor.h:46

↓ 2 callersMethodisRangeOpSubscripted

src/nnet/expr.cc:167

↓ 2 callersMethodisReduced

src/operators/reduce.cc:21

↓ 2 callersMethodisReplaced

include/nnet/ReplaceKit.h:14

↓ 2 callersMethodis_replicate

examples/distributed/placement.py:14

↓ 2 callersFunctionis_unidirectional_broadcasting

src/utils/operator_utils.cc:46

↓ 2 callersMethodless

include/nnet/expr.h:139

↓ 2 callersMethodmagnify

src/nnet/Visitor/RangeMagnifyVisitor.cc:46

↓ 2 callersMethodmatchPatternIT

src/nnet/iterator_table.cc:109

↓ 2 callersMethodmaxPool

src/core/graph_handler.cc:165

↓ 2 callersMethodmerge

src/nnet/Visitor/MergeMemboundMutator.cc:8

↓ 2 callersMethodpopIntermediateState

src/nnet/derivator.cc:450

↓ 2 callersMethodpopRuleMsg

src/nnet/derivator.cc:454

↓ 2 callersMethodpopRuleState

src/nnet/derivator.cc:452

↓ 2 callersMethodprod

include/utils/small_array.h:8

↓ 2 callersMethodpushIntermediateState

src/nnet/derivator.cc:438

↓ 2 callersMethodpushRuleMsg

src/nnet/derivator.cc:446

↓ 2 callersMethodpushRuleState

src/nnet/derivator.cc:442

↓ 2 callersMethodremoveOperator

include/core/graph.h:33

↓ 2 callersMethodresetWorkspace

include/core/workspace.h:35

↓ 2 callersMethodrun

src/kunlun/kunlun_runtime.cc:48

↓ 2 callersMethodrun

src/bang/bang_runtime.cc:56

↓ 2 callersFunctionrunCsrnetOpt

test/nnet/failed/test_csrnet.cc:14

↓ 2 callersFunctionrun_and_compare

(name, model, runtime, world_size=1, rank = 0)

examples/distributed/ascend_launch.py:66

↓ 2 callersFunctionrun_and_compare

(name, model, runtime, world_size=1, rank=0, data_type="default")

examples/distributed/bang/bang_launch.py:79

↓ 2 callersFunctionrun_and_compare

(name, model1, model2, runtime1, runtime2)

examples/distributed/cuda/launch_kvcache.py:125

↓ 2 callersFunctionrun_and_compare

(name, model, runtime, data_type)

examples/distributed/cuda/cuda_launch.py:70

↓ 2 callersFunctionrun_model

(task_name, model, runtime, world_size=1, rank=0,

examples/distributed/kunlun/kunlun_launch.py:119

↓ 2 callersFunctionrun_model

(model1, model2, runtime1, runtime2, inputs1: np.array, inputs2: np.array, n=20)

examples/distributed/cuda/launch_kvcache.py:51

↓ 2 callersFunctionrun_model

(model, runtime, inputs, n=10, data_type = "default")

examples/distributed/cuda/cuda_launch.py:49

↓ 2 callersMethodsetEnableDebug

src/nnet/Pass/Pass.cc:15

↓ 2 callersMethodsetEnableLogging

src/nnet/Pass/Pass.cc:13

↓ 2 callersMethodsetIndex

include/nnet/expr.h:351

↓ 2 callersMethodsetMaxDepth

include/nnet/nmutator.h:29

↓ 2 callersMethodsetTargetOp

src/nnet/derivator.cc:458

↓ 2 callersMethodset_input

(self, inputShapes: List[int])

pyinfinitensor/src/pyinfinitensor/onnx.py:1490

↓ 2 callersFunctionshapeProd

src/utils/operator_utils.cc:120

↓ 2 callersFunctionshard_binary

(node: NodeProto, groups: int = 1)

examples/distributed/parallel_opt.py:71

↓ 2 callersFunctionshard_tensor

(tensor: TensorProto, plc: Shard, groups: int = 1)

examples/distributed/parallel_opt.py:21

↓ 2 callersFunctionshard_tensor

(tensor: TensorProto, dim: int)

examples/distributed/parallel.py:34

↓ 2 callersFunctionstart_interpreter

src/ffi/ffi_embed.cc:5

↓ 2 callersFunctiontestConv3dCudnn

test/kernels/cuda/test_cuda_conv3d.cc:12

↓ 2 callersFunctiontestConvCudnn

test/kernels/cuda/test_cuda_conv.cc:12

↓ 2 callersFunctiontestConvDnnl

test/kernels/intelcpu/test_mkl_conv.cc:12

↓ 2 callersFunctiontestMatmulKUNLUNWithBias

test/kernels/kunlun/test_kunlun_matmul.cc:12

↓ 2 callersFunctiontestMatmulMkl

test/kernels/intelcpu/test_mkl_matmul.cc:13

↓ 2 callersFunctiontest_softmaxFp16

test/kernels/cuda/test_cuda_softmax.cc:38

↓ 2 callersFunctiontest_whereFp16

test/kernels/cuda/test_cuda_where.cc:46

↓ 2 callersMethodtoString

include/core/data_type.h:68

↓ 2 callersMethodtoString

include/bang/cncl_communicator.h:72

↓ 2 callersMethodtopo_sort

src/core/graph.cc:89

↓ 2 callersMethodwhere

src/core/graph_handler.cc:634

↓ 1 callersFunctionConv2gemm_NHWC_RSFC_search

test/nnet/test_conv2gemm.cc:101

↓ 1 callersMethodRoPE

src/core/graph_handler.cc:399

↓ 1 callersFunction_take_shape_dim

(shape: TensorShapeProto)

pyinfinitensor/src/pyinfinitensor/onnx.py:1559

↓ 1 callersFunctionadd_const_value_infos_to_graph

(graph : onnx.GraphProto)

examples/distributed/kunlun/run_pytorch.py:180

↓ 1 callersFunctionadd_const_value_infos_to_graph

(graph : onnx.GraphProto)

examples/distributed/bang/run_pytorch_mlu.py:182

↓ 1 callersFunctionadd_const_value_infos_to_graph

(graph : onnx.GraphProto)

examples/distributed/cuda/run_pytorch.py:122

↓ 1 callersFunctionadd_value_info_for_constants

Currently onnx.shape_inference doesn't use the shape of initializers, so add that info explicitly as ValueInfoProtos. Mutates the model.

examples/distributed/cuda/run_pytorch.py:110

↓ 1 callersFunctionallGather

test/kernels/bang/test_bang_all_gather.cc:15

↓ 1 callersMethodallGather

src/core/graph_handler.cc:557

↓ 1 callersMethodallReduceAvg

src/core/graph_handler.cc:548

↓ 1 callersMethodallReduceMax

src/core/graph_handler.cc:539

↓ 1 callersMethodallReduceMin

src/core/graph_handler.cc:530

↓ 1 callersMethodallReduceProd

src/core/graph_handler.cc:520

← previous next →301–400 of 2,429, ranked by callers