Functions — github.com/OpenPPL/ppl.nn

CodeHub MCPcopy Create free account

hub / github.com/OpenPPL/ppl.nn / functions

Functions6,859 in github.com/OpenPPL/ppl.nn

⨍ Functions 6,859◇ Types & classes 1,448

↓ 2 callersFunctionCreatePoolingParam

src/ppl/nn/models/pmx/generated/onnx_op_generated.h:1976

↓ 2 callersFunctionCreateRMSNormParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:747

↓ 2 callersFunctionCreateReduceParam

src/ppl/nn/models/pmx/generated/onnx_op_generated.h:2066

↓ 2 callersFunctionCreateReshapeParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:1114

↓ 2 callersFunctionCreateRotaryPositionEmbeddingParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:832

↓ 2 callersFunctionCreateRowParallelLinearParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:907

↓ 2 callersFunctionCreateRuntimeImpl

tests/runtime/runtime_impl_test.cc:27

↓ 2 callersFunctionCreateShapeOperationParam

src/ppl/nn/models/pmx/generated/pmx_op_generated.h:191

↓ 2 callersFunctionCreateSliceParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:1196

↓ 2 callersFunctionCreateSplitParam

src/ppl/nn/models/pmx/generated/onnx_op_generated.h:2383

↓ 2 callersFunctionCreateSplitParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:1279

↓ 2 callersFunctionCreateSqueezeParam

src/ppl/nn/models/pmx/generated/onnx_op_generated.h:2489

↓ 2 callersFunctionCreateSwishParam

src/ppl/nn/engines/llm_cuda/pmx/generated/llm_cuda_op_params_generated.h:1338

↓ 2 callersFunctionCreateTransposeParam

src/ppl/nn/models/pmx/generated/onnx_op_generated.h:2601

↓ 2 callersFunctionCreateUnsqueezeParam

src/ppl/nn/models/pmx/generated/onnx_op_generated.h:2652

↓ 2 callersFunctionDelActivationNode

src/ppl/nn/engines/arm/optimizer/rules/utils.cc:306

↓ 2 callersFunctionDeserializeArgMaxParam

src/ppl/nn/models/pmx/oputils/onnx/argmax.cc:28

↓ 2 callersFunctionDeserializeBatchNormalizationParam

src/ppl/nn/models/pmx/oputils/onnx/batch_normalization.cc:28

↓ 2 callersFunctionDeserializeConcatParam

src/ppl/nn/models/pmx/oputils/onnx/concat.cc:28

↓ 2 callersFunctionDeserializeConvParam

src/ppl/nn/models/pmx/oputils/onnx/conv.cc:33

↓ 2 callersMethodDeserializeData

src/ppl/nn/engines/arm/engine.cc:180

↓ 2 callersFunctionDeserializeFlattenParam

src/ppl/nn/models/pmx/oputils/onnx/flatten.cc:28

↓ 2 callersFunctionDeserializeLeakyReluParam

src/ppl/nn/models/pmx/oputils/onnx/leaky_relu.cc:28

↓ 2 callersFunctionDeserializePadParam

src/ppl/nn/models/pmx/oputils/onnx/pad.cc:28

↓ 2 callersFunctionDeserializeResizeParam

src/ppl/nn/models/pmx/oputils/onnx/resize.cc:30

↓ 2 callersFunctionDeserializeSoftmaxParam

src/ppl/nn/models/pmx/oputils/onnx/softmax.cc:28

↓ 2 callersFunctionDeserializeSplitParam

src/ppl/nn/models/pmx/oputils/onnx/split.cc:29

↓ 2 callersFunctionDeserializeSqueezeParam

src/ppl/nn/models/pmx/oputils/onnx/squeeze.cc:29

↓ 2 callersFunctionDeserializeTopKParam

src/ppl/nn/models/pmx/oputils/onnx/topk.cc:28

↓ 2 callersFunctionDeserializeTransposeParam

src/ppl/nn/models/pmx/oputils/onnx/transpose.cc:29

↓ 2 callersFunctionDeserializeUnsqueezeParam

src/ppl/nn/models/pmx/oputils/onnx/unsqueeze.cc:29

↓ 2 callersFunctionDims2Str

tools/pplnn.py:557

↓ 2 callersFunctionDoFindPredecessors

src/ppl/nn/ir/graph_topo.cc:192

↓ 2 callersFunctionDumpOutputTensors

src/ppl/nn/engines/cuda/kernel.cc:38

↓ 2 callersMethodExecute

src/ppl/nn/engines/arm/kernel.cc:60

↓ 2 callersFunctionFinalizeNccl

tools/test_nccl.cc:61

↓ 2 callersMethodFind

src/ppl/nn/utils/op_info_manager.h:73

↓ 2 callersFunctionFindConsumer

src/ppl/nn/auxtools/validate_graph.h:49

↓ 2 callersMethodFindLeafNodes

src/ppl/nn/ir/graph_topo.cc:280

↓ 2 callersFunctionFp16ToFp32

src/ppl/nn/engines/arm/utils/data_trans.cc:34

↓ 2 callersMethodFree

src/ppl/nn/engines/llm_cuda/plain_device.cc:62

↓ 2 callersMethodGather

src/ppl/nn/params/pmx/shape_operation_param.h:56

↓ 2 callersFunctionGenEdgeLastConsumer

src/ppl/nn/runtime/utils.cc:86

↓ 2 callersFunctionGenNodeIdStr

src/ppl/nn/auxtools/to_graphviz.h:28

↓ 2 callersFunctionGenOutputFileName

src/ppl/nn/models/pmx/utils.h:33

↓ 2 callersFunctionGenRandDim

tests/common/tensor_buffer_info_tools.h:27

↓ 2 callersFunctionGenRandDim

tests/runtime/tensor_impl_test.cc:28

↓ 2 callersFunctionGenericLoadConstant

src/ppl/nn/engines/utils.cc:86

↓ 2 callersMethodGetAllocatedSize

src/ppl/nn/utils/buffered_cpu_allocator.h:35

↓ 2 callersMethodGetBarrier

src/ppl/nn/runtime/edge_object.h:53

↓ 2 callersFunctionGetBasename

tools/pplnn_llm.cc:504

↓ 2 callersMethodGetBiasTerm

src/ppl/nn/engines/x86/optimizer/ops/onnx/conv_op.h:39

↓ 2 callersMethodGetCublasAlgoCache

src/ppl/nn/engines/llm_cuda/llm_cuda_device.h:124

↓ 2 callersMethodGetDevice

src/ppl/nn/engines/arm/engine_context.h:35

↓ 2 callersMethodGetDevice

src/ppl/nn/engines/riscv/engine_context.h:34

↓ 2 callersMethodGetDevice

src/ppl/nn/engines/llm_cuda/engine_context.h:39

↓ 2 callersMethodGetElementCount

src/ppl/nn/runtime/tensor_sequence.h:38

↓ 2 callersMethodGetExtraInput

src/ppl/nn/ir/graph_topo.cc:93

↓ 2 callersMethodGetExtraInputTensorImpl

src/ppl/nn/runtime/runtime_impl.h:54

↓ 2 callersFunctionGetFileSize

src/ppl/nn/utils/utils.cc:43

↓ 2 callersMethodGetInput

src/ppl/nn/ir/graph_topo.cc:77

↓ 2 callersMethodGetMaxOptLevel

src/ppl/nn/engines/arm/optimizer/opt_rule_manager.cc:32

↓ 2 callersMethodGetMilliSecond

tools/benchmark_llama/profiler.h:105

↓ 2 callersMethodGetNode

src/ppl/nn/ir/partial_graph_topo.cc:189

↓ 2 callersFunctionGetQuantizeNodeName

src/ppl/nn/engines/llm_cuda/passes/i8i8/quantization_pass.cc:39

↓ 2 callersFunctionGetRelueType

src/ppl/nn/engines/cuda/params/conv_extra_param.cc:29

↓ 2 callersFunctionGetSliceParam

src/ppl/nn/engines/arm/optimizer/rules/fuse_channel_shuffle.cc:29

↓ 2 callersFunctionGetSliceParam

src/ppl/nn/engines/x86/optimizer/rules/fuse_channel_shuffle.cc:30

↓ 2 callersFunctionGetSliceParam

src/ppl/nn/engines/riscv/optimizer/rules/fuse_channel_shuffle.cc:33

↓ 2 callersMethodGetStream

src/ppl/nn/engines/llm_cuda/kernel.h:44

↓ 2 callersMethodGetTensor

src/ppl/nn/runtime/runtime_impl.cc:338

↓ 2 callersMethodGraphRunnerAddDevice

src/ppl/nn/engines/cuda/graph_scheduler.cc:164

↓ 2 callersMethodHasFuseReLU

src/ppl/nn/engines/arm/optimizer/ops/onnx/mul_op.h:39

↓ 2 callersMethodHasFuseReLU

src/ppl/nn/engines/x86/optimizer/ops/onnx/mul_op.h:37

↓ 2 callersMethodHasFuseReLU

src/ppl/nn/engines/riscv/optimizer/ops/onnx/mul_op.h:40

↓ 2 callersMethodInit

src/ppl/nn/utils/file_data_stream.cc:31

↓ 2 callersMethodInit

src/ppl/nn/engines/riscv/optimizer/ops/onnx/log_op.cc:25

↓ 2 callersMethodInit

src/ppl/nn/engines/cuda/engine.cc:70

↓ 2 callersFunctionInitCudaThread

tools/test_nccl.cc:43

↓ 2 callersFunctionInitNccl

tools/test_nccl.cc:51

↓ 2 callersFunctionInitNewSharedResource

src/ppl/nn/engines/common/onnx/if_op.cc:39

↓ 2 callersMethodIsBufferOwner

src/ppl/nn/runtime/tensor_impl.h:65

↓ 2 callersFunctionIsGraphOutput

src/ppl/nn/optimizers/fuse_shape_optimizer.cc:17

↓ 2 callersFunctionIsGraphOutput

src/ppl/nn/optimizers/fuse_parallel_node_optimizer.cc:28

↓ 2 callersFunctionIsInTheSamePartition

src/ppl/nn/optimizers/engine_graph_partitioner.cc:77

↓ 2 callersFunctionN8cxToNdarrayFp32

src/ppl/nn/engines/riscv/utils/data_trans.cc:67

↓ 2 callersFunctionNdarrayToN8cxFp32

src/ppl/nn/engines/riscv/utils/data_trans.cc:96

↓ 2 callersMethodOptimize

src/ppl/nn/optimizers/fuse_bn_optimizer.cc:374

↓ 2 callersFunctionParseInShapes

(in_shapes_str)

tools/pplnn.py:177

↓ 2 callersFunctionParseInputShapes

tools/pplnn.cc:151

↓ 2 callersFunctionParseLabels

src/ppl/nn/oputils/onnx/reshape_einsum.cc:29

↓ 2 callersFunctionParseOneInitializerData

src/ppl/nn/models/onnx/graph_parser.cc:31

↓ 2 callersFunctionParseOneInputData

src/ppl/nn/models/onnx/graph_parser.cc:78

↓ 2 callersFunctionParseOneNodeData

src/ppl/nn/models/onnx/graph_parser.cc:206

↓ 2 callersFunctionParseOneNodeTopo

src/ppl/nn/models/onnx/graph_parser.cc:149

↓ 2 callersMethodPopRequests

tools/benchmark_llama/request.h:144

↓ 2 callersMethodPrepareGeneration

tools/benchmark_llama/text_generator.cc:181

↓ 2 callersFunctionQuantizeLinearSelfDequant

src/ppl/nn/engines/llm_cuda/passes/i8i8/quantization_pass.cc:372

↓ 2 callersFunctionQuantizeWeight

return scale edge

src/ppl/nn/engines/llm_cuda/passes/i8i8/quantization_pass.cc:53

↓ 2 callersMethodRealloc

src/ppl/nn/engines/arm/arm_device.h:55

← previous next →501–600 of 6,859, ranked by callers