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

↓ 1 callersFunctionallReduceSum

test/bang/test_cncl_comm.cc:10

↓ 1 callersMethodallocWeight

src/core/lazy_allocator.cc:111

↓ 1 callersMethodattentionKVCache

src/core/graph_handler.cc:378

↓ 1 callersMethodbatchNormalization

src/core/graph_handler.cc:103

↓ 1 callersFunctionbitPosition

src/nnet/Pass/Rule8GuidedDLT.cc:15

↓ 1 callersFunctionbroadcast

test/kernels/bang/test_bang_broadcast.cc:16

↓ 1 callersMethodbroadcast

src/core/graph_handler.cc:568

↓ 1 callersFunctionbuildAnsNegNeg

L<x:0:2><y:0:4>Sum ... [(((-1 * x) + (-2 * y)) + 7)] {L<i1:0:8>Sum<t1:0:5> {({A}[i1] * {B}[t1])}}

test/nnet/test_Rule2VariableMerging.cc:102

↓ 1 callersFunctionbuildAnsPosNeg

L<x:0:2><y:0:4>Sum ... [((x + (-2 * y)) + 6)] {L<i1:0:8>Sum<t1:0:5> {({A}[i1] * {B}[t1])}}}

test/nnet/test_Rule2VariableMerging.cc:68

↓ 1 callersFunctionbuildAnsPosPos

L<x:0:2><y:0:4>Sum ... [(x + (2 * y))] {L<i3:0:8>Sum<t1:0:5> {({A}[i3] * {B}[t1])}}

test/nnet/test_Rule2VariableMerging.cc:13

↓ 1 callersFunctionbuildConv

test/nnet/test_compareFormulas.cc:9

↓ 1 callersMethodbuildExpr

src/nnet/iterator_table.cc:269

↓ 1 callersFunctionbuildNestedExpr

test/nnet/test_serializer.cc:30

↓ 1 callersFunctionbuildSimpleExpr

test/nnet/test_serializer.cc:14

↓ 1 callersFunctionbuildTConv4x4_NHWF_FRSC

Warn: F is the number of input channels, which is inversed compared with normal Conv. Our data layout: NHWF -> NHWC, FRSC Pytorch data layout: NFHW ->

test/nnet/test_TConv2gemm.cc:182

↓ 1 callersFunctionbuildTConv4x4_NHWF_RSFC

Warn: F is the number of input channels, which is inversed compared with normal Conv. Our data layout: NHWF -> NHWC, RSFC Pytorch data layout: NFHW ->

test/nnet/test_OpSearch.cc:98

↓ 1 callersMethodcast

src/core/graph_handler.cc:611

↓ 1 callersMethodchange_shape

src/core/graph_handler.cc:793

↓ 1 callersFunctioncheckExprsEquvivalence

src/nnet/test.cc:64

↓ 1 callersMethodcheckOOB

src/nnet/derivator.cc:416

↓ 1 callersFunctioncheckShape

src/operators/gather_elements.cc:13

↓ 1 callersMethodcheckValid

tensor's "source" and "target" must be in "ops". tensor has no "source" and no "target" must not exist. "inputs" or "outputs" of operators must be in

src/core/graph.cc:354

↓ 1 callersMethodclip

src/core/graph_handler.cc:260

↓ 1 callersMethodcloneKV

src/core/graph.cc:270

↓ 1 callersMethodcloneOperator

include/core/graph.h:49

↓ 1 callersMethodcompute

src/kernels/cuda/conv.cc:170

↓ 1 callersMethodcompute

src/kernels/cuda/element_wise.cc:13

↓ 1 callersMethodcompute

include/core/kernel.h:171

↓ 1 callersFunctioncomputeDifference1

src/utils/validation.cc:11

↓ 1 callersFunctioncomputeDifference3

src/utils/validation.cc:28

↓ 1 callersFunctioncomputeDifference4

src/utils/validation.cc:38

↓ 1 callersFunctioncomputeDifference5

src/utils/validation.cc:48

↓ 1 callersMethodconcat

src/core/graph_handler.cc:369

↓ 1 callersMethodcopyBlob

src/core/runtime.cc:131

↓ 1 callersMethodcopyBlobFromCPU

include/cuda/cuda_runtime.h:71

↓ 1 callersMethodcopyData

include/core/tensor.h:114

↓ 1 callersMethodcopyout

include/core/tensor.h:85

↓ 1 callersFunctioncuDataType2ComputeType

src/kernels/cuda/matmul.cc:37

↓ 1 callersFunctiondecimalToBinary

include/nnet/dbg.h:531

↓ 1 callersMethoddeleteConnection

src/core/graph.cc:318

↓ 1 callersMethoddepthToSpace

src/core/graph_handler.cc:648

↓ 1 callersFunctiondevice_to_str

src/utils/operator_utils.cc:94

↓ 1 callersFunctiondtype_repr_convert

src/core/graph_handler.cc:756

↓ 1 callersMethodelu

src/core/graph_handler.cc:40

↓ 1 callersMethodexpand

src/core/graph_handler.cc:623

↓ 1 callersFunctionexport_functions

src/ffi/ffi_infinitensor.cc:349

↓ 1 callersFunctionexport_onnx

(model: LlamaModel, ONNX_MODEL_PATH)

examples/python/llama_kvcache_inference.py:26

↓ 1 callersFunctionexport_onnx

(model_name, model, data, path, extern=False)

examples/distributed/kunlun/run_pytorch.py:111

↓ 1 callersFunctionexport_onnx

(modelname, model, data, path, extern=False, dtype="fp32")

examples/distributed/bang/run_pytorch_mlu.py:101

↓ 1 callersFunctionexport_onnx

(model, data, path, extern=False)

examples/distributed/cuda/run_pytorch.py:89

↓ 1 callersFunctionexport_values

src/ffi/ffi_infinitensor.cc:65

↓ 1 callersFunctionfind_successor

(op_type: str, idx: int, search_limit: int = 1)

examples/distributed/parallel_opt.py:159

↓ 1 callersFunctionfp16_to_float

src/utils/data_convert.cc:18

↓ 1 callersMethodfreeHeap

src/core/graph.cc:289

↓ 1 callersFunctionfrom_json

src/core/perf_engine.cc:28

↓ 1 callersMethodgather

src/core/graph_handler.cc:436

↓ 1 callersMethodgatherElements

src/core/graph_handler.cc:450

↓ 1 callersFunctiongen_standard

(task_name: str, model: onnx.ModelProto)

examples/distributed/kunlun/kunlun_launch.py:206

↓ 1 callersFunctiongen_standard

(name, model1, model2, voc_size, bs, len)

examples/distributed/cuda/launch_kvcache.py:195

↓ 1 callersFunctiongen_standard

(name, model, voc_size, bs, len)

examples/distributed/cuda/cuda_launch.py:109

↓ 1 callersFunctiongenerate_input_output

examples/distributed/bang/bang_launch.py:114

↓ 1 callersMethodget

include/core/data_type.h:64

↓ 1 callersMethodgetB

include/operators/G2BMM.h:48

↓ 1 callersMethodgetBMKWD

include/operators/G2BMM.h:51

↓ 1 callersMethodgetBMWND

include/operators/GBMM.h:49

↓ 1 callersMethodgetBias

include/operators/GBMM.h:42

↓ 1 callersMethodgetBlockSize

include/operators/transpose.h:33

↓ 1 callersFunctiongetCuComputeType

src/kernels/cuda/matmul.cc:51

↓ 1 callersMethodgetData

src/nnet/expr.cc:62

↓ 1 callersFunctiongetDiff

examples/distributed/ascend_launch.py:144

↓ 1 callersMethodgetDilation

include/operators/G2BMM.h:44

↓ 1 callersMethodgetDilation

include/operators/GBMM.h:41

↓ 1 callersFunctiongetFormat

A helper function that converts DataType to python format string

src/ffi/ffi_infinitensor.cc:398

↓ 1 callersMethodgetFormulaStride

include/nnet/Visitor/StrideVisitor.h:19

↓ 1 callersMethodgetHeapPtr

src/core/lazy_allocator.cc:202

↓ 1 callersMethodgetIterDimInTensor

src/nnet/iterator_table.cc:98

↓ 1 callersMethodgetKh

include/operators/pooling.h:49

↓ 1 callersMethodgetKw

include/operators/pooling.h:50

↓ 1 callersFunctiongetLength

include/nnet/expr.h:204

↓ 1 callersMethodgetLogMode

src/nnet/derivator.cc:529

↓ 1 callersMethodgetM

include/operators/G2BMM.h:49

↓ 1 callersMethodgetMemPoolStatus

src/core/lazy_allocator.cc:59

↓ 1 callersMethodgetModeString

include/operators/transpose.h:35

↓ 1 callersMethodgetNumIntermediateStates

src/nnet/derivator.cc:143

↓ 1 callersMethodgetNumRows

include/nnet/iterator_table.h:86

↓ 1 callersMethodgetObjectRangesWithoutPaddings

src/nnet/expr.cc:171

↓ 1 callersMethodgetOutputDataType

src/operators/unary.cc:184

↓ 1 callersFunctiongetPReluExpr

test/nnet/test_memboundOp.cc:99

↓ 1 callersFunctiongetPatternName

src/nnet/iterator_table.cc:513

↓ 1 callersFunctiongetProjectHome

src/nnet/test.cc:9

↓ 1 callersMethodgetReduction

include/operators/element_wise.h:43

↓ 1 callersMethodgetResult

include/nnet/Visitor/MatchTableVisitor.h:55

↓ 1 callersMethodgetReverseMap

src/nnet/iterator_table.cc:256

↓ 1 callersMethodgetScale

src/kernels/bang/activation.cc:14

↓ 1 callersMethodgetSimplifiedNnetExpr

include/operators/membound.h:30

↓ 1 callersMethodgetTrainingMode

include/operators/dropout.h:46

↓ 1 callersMethodgetW

include/operators/GBMM.h:47

↓ 1 callersMethodgetWeightPtr

src/core/lazy_allocator.cc:186

↓ 1 callersMethodgetWidth

include/operators/G2BMM.h:43

↓ 1 callersMethodgetWorkspace

Get $size workspace by bytes

include/kunlun/kunlun_runtime.h:52

← previous next →401–500 of 2,429, ranked by callers