Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/InfiniTensor/InfiniTensor
/ functions
Functions
2,429 in github.com/InfiniTensor/InfiniTensor
⨍
Functions
2,429
◇
Types & classes
632
↓ 4 callers
Method
getNumInputs
include/nnet/iterator_table.h:84
↓ 4 callers
Function
getOffset
test/nnet/test_TConv2gemm.cc:278
↓ 4 callers
Method
getOps
include/core/graph_match.h:67
↓ 4 callers
Method
getReshapeDim
include/operators/transpose.h:36
↓ 4 callers
Method
getScales
include/operators/resize.h:134
↓ 4 callers
Method
getSourceRank
include/operators/send.h:30
↓ 4 callers
Method
guidedDLT
src/nnet/Pass/Rule8GuidedDLT.cc:27
↓ 4 callers
Method
hasData
include/core/tensor_base.h:37
↓ 4 callers
Method
init
src/operators/resize.cc:28
↓ 4 callers
Method
interpretUniformSample
src/nnet/Visitor/Interpreter.cc:153
↓ 4 callers
Method
isMatMulOrConv
src/core/op_type.cc:280
↓ 4 callers
Method
is_shard
(self, dim: Optional[int] = None)
examples/distributed/placement.py:8
↓ 4 callers
Method
matchWithPattern
src/nnet/Visitor/PatternMatcher.cc:116
↓ 4 callers
Method
removeTensor
include/core/graph.h:39
↓ 4 callers
Method
replaceSubGraph
replace all sub graphs which matched subA with subB in g
src/core/graph_match.cc:300
↓ 4 callers
Method
runWithCudaGraph
src/cuda/cuda_runtime.cc:42
↓ 4 callers
Method
serialize
src/nnet/Visitor/Serializer.cc:76
↓ 4 callers
Function
serializeVec
include/nnet/expr.h:86
↓ 4 callers
Method
softmax
src/core/graph_handler.cc:270
↓ 4 callers
Function
test_layernormFp32
test/kernels/cuda/test_cuda_layernorm.cc:11
↓ 4 callers
Function
test_reducemean
test/kernels/intelcpu/test_mkl_reduce.cc:11
↓ 4 callers
Function
test_softmaxFp32
test/kernels/cuda/test_cuda_softmax.cc:11
↓ 4 callers
Function
test_where
test/kernels/kunlun/test_kunlun_where.cc:10
↓ 4 callers
Function
test_whereFp32
test/kernels/cuda/test_cuda_where.cc:11
↓ 4 callers
Method
toString
src/kunlun/kunlun_runtime.cc:58
↓ 4 callers
Method
tune
(self)
pyinfinitensor/src/pyinfinitensor/onnx.py:1504
↓ 4 callers
Method
tune
src/cuda/cuda_runtime.cc:63
↓ 3 callers
Method
addOp
src/core/graph_match.cc:13
↓ 3 callers
Method
addPredecessors
include/core/operator.h:124
↓ 3 callers
Method
addSuccessors
include/core/operator.h:125
↓ 3 callers
Function
check_exists
(path: str)
examples/distributed/kunlun/kunlun_launch.py:80
↓ 3 callers
Function
cnclDataTypeConvert
include/bang/bang_common.h:67
↓ 3 callers
Method
compare
src/nnet/Visitor/CompareMultiFormulasVisitor.cc:5
↓ 3 callers
Method
computeFuncTune
Find the optimal computing function by comparing its running time
include/core/kernel.h:64
↓ 3 callers
Method
freeData
include/core/tensor_base.h:38
↓ 3 callers
Method
getAnchorByPattern
include/core/graph_match.h:55
↓ 3 callers
Method
getComputeOps
src/core/graph.cc:310
↓ 3 callers
Method
getDType
HACK: set correct data type
include/core/operator.h:92
↓ 3 callers
Method
getDh
include/operators/conv.h:105
↓ 3 callers
Method
getDw
include/operators/conv.h:106
↓ 3 callers
Method
getEnds
include/operators/slice.h:46
↓ 3 callers
Method
getK
include/operators/G2BMM.h:50
↓ 3 callers
Method
getNewVar
src/nnet/Pass/Pass.cc:27
↓ 3 callers
Method
getNnetExpr
include/operators/membound.h:29
↓ 3 callers
Method
getPh
include/operators/conv.h:107
↓ 3 callers
Method
getPtr
src/core/lazy_allocator.cc:170
↓ 3 callers
Method
getPw
include/operators/conv.h:108
↓ 3 callers
Method
getRoot
include/operators/broadcast.h:35
↓ 3 callers
Method
getSh
include/operators/conv.h:109
↓ 3 callers
Method
getSteps
include/operators/slice.h:52
↓ 3 callers
Method
getStmts
src/nnet/Visitor/AsTVMVisitor.cc:169
↓ 3 callers
Method
getStridesInTensor
src/nnet/iterator_table.cc:94
↓ 3 callers
Method
getSubscript
include/nnet/iterator_table.h:107
↓ 3 callers
Method
getSw
include/operators/conv.h:110
↓ 3 callers
Method
getTensor
src/core/graph.cc:130
↓ 3 callers
Method
getTransposeDim
include/operators/transpose.h:37
↓ 3 callers
Method
getWorkspaceAlloc
include/core/workspace.h:39
↓ 3 callers
Method
getXcclComm
include/kunlun/xccl_communicator.h:50
↓ 3 callers
Method
hasContained
include/core/graph_match.h:50
↓ 3 callers
Method
hasLoopVar
include/nnet/expr.h:245
↓ 3 callers
Function
hashVector
include/core/hash.h:11
↓ 3 callers
Function
idToRoutineType
include/nnet/expr.h:41
↓ 3 callers
Method
interpretAllOutput
src/nnet/Visitor/Interpreter.cc:170
↓ 3 callers
Function
is_sharded
(name: str)
examples/distributed/parallel_opt.py:18
↓ 3 callers
Function
matchConv
test/nnet/test_matchConv.cc:10
↓ 3 callers
Method
neq
include/nnet/expr.h:138
↓ 3 callers
Method
newTensorName
src/nnet/Pass/Pass.cc:29
↓ 3 callers
Function
pretty_print
include/nnet/dbg.h:411
↓ 3 callers
Function
realTest
test/nnet/test_Rule2VariableMerging.cc:30
↓ 3 callers
Method
resetWorkspace
include/bang/bang_runtime.h:60
↓ 3 callers
Method
run
src/cuda/cuda_runtime.cc:101
↓ 3 callers
Method
setDataBlob
src/core/tensor.cc:190
↓ 3 callers
Method
setObject
src/nnet/expr.cc:161
↓ 3 callers
Method
setPadding
include/nnet/expr.h:171
↓ 3 callers
Method
setShape
src/core/tensor.cc:62
↓ 3 callers
Function
test_layernormFp32
test/kernels/ascend/test_ascend_layernorm.cc:11
↓ 3 callers
Method
toReadable
include/nnet/expr.h:136
↓ 3 callers
Method
toString
src/cuda/cuda_runtime.cc:114
↓ 3 callers
Method
what
include/utils/exception.h:19
↓ 3 callers
Function
wrefs_to_refs
include/core/ref.h:36
↓ 2 callers
Method
addTarget
include/core/tensor_base.h:58
↓ 2 callers
Function
add_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/kunlun/run_pytorch.py:168
↓ 2 callers
Function
add_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/bang/run_pytorch_mlu.py:170
↓ 2 callers
Method
allReduceSum
src/core/graph_handler.cc:511
↓ 2 callers
Method
allocBlob
src/core/runtime.cc:127
↓ 2 callers
Method
applyWrapper
src/nnet/Visitor/PatternMatcher.cc:96
↓ 2 callers
Function
bitCount
src/nnet/Pass/Rule8GuidedDLT.cc:6
↓ 2 callers
Function
buildTConv4x4_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_TConv2gemm.cc:224
↓ 2 callers
Function
checkExprLogSame
src/nnet/test.cc:39
↓ 2 callers
Method
clone
include/core/tensor.h:126
↓ 2 callers
Function
computeDifference2
src/utils/validation.cc:19
↓ 2 callers
Method
convTransposed2d
src/core/graph_handler.cc:69
↓ 2 callers
Method
copyBlobToCPU
include/cuda/cuda_runtime.h:76
↓ 2 callers
Method
dataMalloc
include/core/tensor_base.h:32
↓ 2 callers
Function
delocate_index
src/utils/operator_utils.cc:81
↓ 2 callers
Function
float_to_fp16
src/utils/data_convert.cc:5
↓ 2 callers
Function
format_file
(file)
scripts/format.py:11
↓ 2 callers
Method
getAlphaBetaBias
include/operators/lrn.h:17
↓ 2 callers
Method
getBMNK
include/operators/matmul.h:66
↓ 2 callers
Method
getComputeType
include/operators/matmul.h:67
← previous
next →
201–300 of 2,429, ranked by callers