MCPcopy Create free account

hub / github.com/UbiquitousLearning/mllm / functions

Functions5,971 in github.com/UbiquitousLearning/mllm

⨍ Functions 5,971◇ Types & classes 1,855↳ Endpoints 4
↓ 1 callersMethodcaptureAOTGraph
mllm/backends/qnn/aot/QnnWrappersAPI.cpp:667
↓ 1 callersFunctioncapture_backtrace
mllm/mllm.hpp:282
↓ 1 callersFunctioncast
mllm/utils/RTTIHelper.hpp:105
↓ 1 callersMethodchatCompletionsHandler
()
mllm-cli/pkg/server/handlers.go:166
↓ 1 callersFunctionchr
mllm/preprocessor/tokenizers/Unicode.hpp:19
↓ 1 callersFunctionchunk
mllm/nn/Functional.hpp:87
↓ 1 callersFunctioncircular_index
Helper: circular index (wrap)
mllm/backends/cpu/ops/PadOp.cpp:46
↓ 1 callersFunctionclamp
mllm/backends/cpu/kernels/arm/mllm_blas/mllm_blas_i8gemm_bitspack_1x1x32_fp32_neondot.hpp:17
↓ 1 callersFunctioncleanThisThread
mllm/mllm.cpp:106
↓ 1 callersMethodclear
tools/mllm-llm-benchmark/models/Qwen3_W4A32_KAI.hpp:91
↓ 1 callersMethodclearKVCache
mllm/models/qwen_npu/modeling_qwen_npu.hpp:442
↓ 1 callersFunctionclip_fp16
mllm/backends/cpu/kernels/arm/elementwise.cpp:378
↓ 1 callersFunctionclip_fp32
mllm/backends/cpu/kernels/arm/elementwise.cpp:371
↓ 1 callersFunctionclip_int16
mllm/backends/cpu/kernels/arm/elementwise.cpp:391
↓ 1 callersFunctionclip_int32
mllm/backends/cpu/kernels/arm/elementwise.cpp:397
↓ 1 callersFunctionclip_int8
mllm/backends/cpu/kernels/arm/elementwise.cpp:385
↓ 1 callersFunctioncloneQuantizationSpecType
mllm/backends/qnn/aot/passes/LLMQuantRecipePass.cpp:180
↓ 1 callersFunctioncompile
()
playground/cache_reduced_computation/run_remote_android.py:5
↓ 1 callersFunctioncompile
()
playground/cache_reduced_computation/run.py:4
↓ 1 callersFunctioncompile
()
algorithms/fancy_algorithm/run.py:5
↓ 1 callersFunctioncompile
()
algorithms/lazy_vlm/run_remote_android.py:5
↓ 1 callersMethodcompile
mllm/backends/opencl/vendors/OpenCL-Headers/CL/opencl.hpp:7049
↓ 1 callersFunctioncomputeLongRoPEScalingFactor
mllm/models/minicpm4/modeling_minicpm4.hpp:31
↓ 1 callersFunctioncompute_padded_shape
Helper: compute output shape from input shape and pad vector (starting from last dimension)
mllm/backends/cpu/ops/PadOp.cpp:14
↓ 1 callersFunctionconfigEngineWithArgs
mllm/mllm.cpp:29
↓ 1 callersMethodconsumerOps
mllm/compile/ir/Node.cpp:216
↓ 1 callersFunctionconv1d_and_trans_and_viw
mllm/preprocessor/audio/Audio.cpp:286
↓ 1 callersFunctionconv2d_fp32_im2col_input
mllm/backends/cpu/kernels/arm/conv2d.cpp:11
↓ 1 callersFunctionconv2d_fp32_im2col_weight
mllm/backends/cpu/kernels/arm/conv2d.cpp:80
↓ 1 callersFunctionconv3DOpImplType2Str
mllm/core/aops/Conv3DOp.hpp:34
↓ 1 callersFunctionconv3d_fp32_baseline
mllm/backends/cpu/kernels/arm/conv3d.cpp:11
↓ 1 callersMethodconvert
(self)
pymllm/backends/qualcomm/transformers/qwen3/runner.py:346
↓ 1 callersMethodconvert
(self)
pymllm/backends/qualcomm/transformers/qwen2/runner.py:332
↓ 1 callersMethodconvert
(self)
pymllm/backends/qualcomm/transformers/llama/runner.py:325
↓ 1 callersMethodconvert_rope_for_deploy
(self)
pymllm/backends/qualcomm/transformers/qwen3/modeling_qwen3.py:544
↓ 1 callersMethodconvert_rope_for_deploy
(self)
pymllm/backends/qualcomm/transformers/qwen2/modeling_qwen2.py:533
↓ 1 callersMethodconvert_rope_for_deploy
(self)
pymllm/backends/qualcomm/transformers/llama/modeling_llama.py:590
↓ 1 callersFunctioncopyAscendTensorToHost
mllm/backends/ascend/AscendCommon.cpp:83
↓ 1 callersFunctioncopyGraphsInfoV1
mllm/backends/qnn/QNNUtils.cpp:108
↓ 1 callersFunctioncopyGraphsInfoV3
mllm/backends/qnn/QNNUtils.cpp:128
↓ 1 callersFunctioncopyMetadataToGraphsInfo
--------------- QNN Graph Info Copying methods ---------------
mllm/backends/qnn/QNNUtils.cpp:69
↓ 1 callersMethodcopy_files
(self, src_dir, dst_dir)
task.py:358
↓ 1 callersMethodcopy_lm_head_weight_from_embed_tokens
(self)
pymllm/backends/qualcomm/transformers/qwen3/modeling_qwen3.py:713
↓ 1 callersMethodcopy_lm_head_weight_from_embed_tokens
(self)
pymllm/backends/qualcomm/transformers/qwen2/modeling_qwen2.py:702
↓ 1 callersMethodcopy_lm_head_weight_from_embed_tokens
(self)
pymllm/backends/qualcomm/transformers/llama/modeling_llama.py:730
↓ 1 callersFunctioncorrectly_handled_stream
()
pymllm/service/network.py:68
↓ 1 callersMethodcpu
(self)
pymllm/ffi/__init__.py:241
↓ 1 callersMethodcpu
mllm/core/Tensor.cpp:452
↓ 1 callersFunctioncpu_
()
pymllm/ffi/__init__.py:106
↓ 1 callersMethodcreate
(device: Device, options: SoftmaxOpOptions)
pymllm/ffi/__init__.py:644
↓ 1 callersMethodcreate
mllm/backends/qnn/QNNUtils.cpp:452
↓ 1 callersFunctioncreateAscendAllocator
mllm/backends/ascend/AscendAllocator.cpp:107
↓ 1 callersFunctioncreateAscendDispatcher
mllm/backends/ascend/AscendDispatcher.cpp:83
↓ 1 callersFunctioncreateBenchmark
tools/mllm-llm-benchmark/models/All.hpp:11
↓ 1 callersFunctioncreateCF2ProgramPass
mllm/compile/passes/ProgramLoweringPipeline.cpp:282
↓ 1 callersFunctioncreateCPUAllocator
mllm/backends/cpu/CPUAllocator.cpp:102
↓ 1 callersFunctioncreateCPUBackend
mllm/backends/cpu/CPUBackend.cpp:103
↓ 1 callersFunctioncreateCPUDispatcher
mllm/backends/cpu/CPUDispatcher.cpp:76
↓ 1 callersMethodcreateContext
mllm/backends/qnn/aot/QnnWrappersAPI.cpp:494
↓ 1 callersFunctioncreateCpuMemoryDiskDispatcher
mllm/engine/io/CpuMemoryDiskDispatcher.cpp:79
↓ 1 callersFunctioncreateCudaAllocator
mllm/backends/cuda/CudaAllocator.cpp:67
↓ 1 callersFunctioncreateCudaBackend
mllm/backends/cuda/CudaBackend.cpp:32
↓ 1 callersFunctioncreateEagerMemorySolverPass
mllm/compile/passes/EagerMemorySolverPass.cpp:95
↓ 1 callersFunctioncreateEliminateDbgInfoPass
mllm/compile/passes/EliminateDbgInfoPass.cpp:47
↓ 1 callersFunctioncreateExtractConstantTensorPass
mllm/compile/passes/ExtractConstantTensorPass.cpp:81
↓ 1 callersFunctioncreateExtractSymbolsPass
mllm/compile/passes/ExtractSymbolsPass.cpp:78
↓ 1 callersFunctioncreateFlattenTensorAndLinalgSymbol2ProgramSymbolPass
mllm/compile/passes/FlattenTensorAndLinalgSymbol2ProgramSymbolPass.cpp:78
↓ 1 callersFunctioncreateGraph2ProgramPass
mllm/compile/passes/ProgramLoweringPipeline.cpp:242
↓ 1 callersFunctioncreateLLM2QnnLoweringPass
mllm/backends/qnn/aot/passes/LLM2QnnLoweringPass.cpp:194
↓ 1 callersFunctioncreateLLMQuantRecipePass
mllm/backends/qnn/aot/passes/LLMQuantRecipePass.cpp:1172
↓ 1 callersFunctioncreateLinalg2ProgramPass
mllm/compile/passes/ProgramLoweringPipeline.cpp:95
↓ 1 callersFunctioncreateMarkQnnGraphPass
mllm/backends/qnn/aot/passes/MarkQnnGraphPass.cpp:75
↓ 1 callersFunctioncreateMarkTensorIOPass
mllm/backends/qnn/aot/passes/MarkTensorIO.cpp:120
↓ 1 callersMethodcreateMemoryPool
mllm/backends/ascend/memory/AscendMemoryManager.cpp:20
↓ 1 callersFunctioncreateMergeLLMHeadIntoMainGraphPass
mllm/backends/qnn/aot/passes/MergeLLMHeadIntoMainGraphPass.cpp:111
↓ 1 callersFunctioncreateOpNamingPass
mllm/backends/qnn/aot/passes/OpNamingPass.cpp:88
↓ 1 callersFunctioncreateOpenCLDispatcher
mllm/backends/opencl/OpenCLDispatcher.cpp:77
↓ 1 callersFunctioncreatePTQPass
mllm/backends/qnn/aot/passes/PTQPass.cpp:504
↓ 1 callersFunctioncreateProgramIntrinsicIdIndexPass
mllm/compile/passes/ProgramIntrinsicIdIndexPass.cpp:58
↓ 1 callersFunctioncreateProgramModeConfigPass
mllm/compile/passes/ProgramModeConfigPass.cpp:23
↓ 1 callersFunctioncreateQNNAllocator
mllm/backends/qnn/QNNAllocator.cpp:122
↓ 1 callersFunctioncreateQNNDispatcher
mllm/backends/qnn/QNNDispatcher.cpp:86
↓ 1 callersMethodcreateQnnGraph
mllm/backends/qnn/QNNBackend.cpp:562
↓ 1 callersFunctioncreateSplitLLMGraphPass
mllm/backends/qnn/aot/passes/SplitLLMGraphPass.cpp:233
↓ 1 callersFunctioncreateTensor2ProgramPass
mllm/compile/passes/ProgramLoweringPipeline.cpp:333
↓ 1 callersFunctioncreate_basis_tensor
Create basis tensor: cumulative product of [1] + levels[:-1]
mllm/models/minicpm_o2_6/modeling_vector_quantize.hpp:43
↓ 1 callersMethodcreate_context
( self, name: str, weights_sharing: bool = False )
pymllm/ffi/__init__.py:619
↓ 1 callersFunctioncreate_hann_window
Create a Hann window
mllm/models/minicpm_o2_6/audio_preprocessor_minicpmo.hpp:44
↓ 1 callersFunctioncreate_levels_tensor
Create tensor from vector values
mllm/models/minicpm_o2_6/modeling_vector_quantize.hpp:35
↓ 1 callersFunctioncreate_mel_filterbank
Create mel filter bank matrix
mllm/models/minicpm_o2_6/audio_preprocessor_minicpmo.hpp:61
↓ 1 callersMethodcuda
mllm/core/Tensor.cpp:457
↓ 1 callersFunctioncuda_
()
pymllm/ffi/__init__.py:110
↓ 1 callersFunctioncut_and_trans
mllm/preprocessor/audio/Audio.cpp:318
↓ 1 callersFunctiondecodeBase64Image
(uri string)
mllm-cli/pkg/server/handlers.go:18
↓ 1 callersMethoddecodeEventEndTimePoint
mllm/models/ARGeneration.cpp:502
↓ 1 callersMethoddecodeEventStartTimePoint
mllm/models/ARGeneration.cpp:500
↓ 1 callersMethoddecodeToMelSpecs
* Decode discrete audio codes to mel spectrograms * * Borrowed from ChatTTS implementation. Converts discrete audio codes from generate() * i
mllm/models/minicpm_o2_6/modeling_chattts.hpp:450
↓ 1 callersMethoddecreaseIndent
mllm/compile/ir/IRPrinter.hpp:62
↓ 1 callersFunctiondefine_builtin_ir
(ir: dict)
mllm/compile/ir/rtti_kind_gen.py:194
↓ 1 callersFunctiondefine_control_flow_ir
(ir: dict)
mllm/compile/ir/rtti_kind_gen.py:334
← previousnext →1,101–1,200 of 5,971, ranked by callers