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 callersFunctionew_sub_int8_scalar
mllm/backends/cpu/kernels/arm/elementwise.cpp:212
↓ 1 callersFunctionextractGroupName
tools/mllm-quantizer/driver.cpp:13
↓ 1 callersFunctionfilter_files
(directory, patterns, ignore_dirs=None, r=True, case_sensitive=True)
task.py:37
↓ 1 callersMethodfinalize
(self)
pymllm/convertor/model_file_v2.py:263
↓ 1 callersMethodfinalize
(self, cls: Cls)
mllm/compile/ir/rtti_kind_gen.py:127
↓ 1 callersFunctionfindClosestAspectRatio
mllm/models/deepseek_ocr/conversation_preprocess.hpp:362
↓ 1 callersFunctionfind_min_and_max
mllm/backends/cpu/kernels/arm/quantize/bitspack/bitspack.cpp:47
↓ 1 callersFunctionflashAttnSWAwSink
mllm-ext-opset/cpu/fa2_swa_sink/tests/main.cpp:7
↓ 1 callersFunctionfloat16_
()
pymllm/ffi/__init__.py:59
↓ 1 callersFunctionfloat32_
()
pymllm/ffi/__init__.py:55
↓ 1 callersFunctionfloat_to_bits
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/LLaMASuperSiLU.cpp:110
↓ 1 callersFunctionformatMessages
mllm/models/deepseek_ocr/conversation_preprocess.hpp:288
↓ 1 callersMethodforward
(self, *args)
pymllm/nn/_module.py:59
↓ 1 callersMethodforward
(self, *args)
pymllm/nn/_layers.py:23
↓ 1 callersMethodforward
mllm/models/qwen3/modeling_qwen3.hpp:86
↓ 1 callersMethodforward
* Forward pass */
mllm/models/minicpm_o2_6/modeling_vector_quantize.hpp:319
↓ 1 callersMethodforward
mllm/models/minicpm_o2_6/modeling_dvae.hpp:126
↓ 1 callersMethodforward
tests/plugin/CustomPackageForHostTest.hpp:18
↓ 1 callersMethodforward
examples/llama_qnn_aot/modeling_llama_qnn_aot.hpp:160
↓ 1 callersFunctionfp16_2_fp32
mllm/backends/cpu/kernels/arm/cast_types.cpp:172
↓ 1 callersFunctionfp32_2_fp16
mllm/backends/cpu/kernels/arm/cast_types.cpp:144
↓ 1 callersFunctionfreeQnnTensor
mllm/backends/qnn/QNNUtils.cpp:281
↓ 1 callersMethodfreeze_activation
(self)
pymllm/backends/qualcomm/transformers/qwen3/runner.py:218
↓ 1 callersMethodfreeze_activation
(self)
pymllm/backends/qualcomm/transformers/qwen2/runner.py:218
↓ 1 callersMethodfreeze_activation
(self)
pymllm/backends/qualcomm/transformers/llama/runner.py:218
↓ 1 callersMethodfreeze_weight
Manually trigger Observer to observe and calculate scale, then lock it. Solve the problem of output being 0 on first run.
pymllm/backends/qualcomm/transformers/core/rms_norm.py:106
↓ 1 callersMethodfreeze_weight
Manually trigger Observer to observe and calculate scale, then lock it. Solve the problem of output being 0 on first run.
pymllm/backends/qualcomm/transformers/core/embedding.py:111
↓ 1 callersFunctionfrom_numpy
(numpy_tensor)
pymllm/ffi/__init__.py:367
↓ 1 callersFunctionfrom_torch
(torch_tensor)
pymllm/ffi/__init__.py:363
↓ 1 callersMethodfunction_name
mllm-kernel/include/mllm_kernel/source_location.hpp:33
↓ 1 callersFunctiongelu_fp16
mllm/backends/cpu/kernels/arm/gelu.cpp:123
↓ 1 callersMethodgen_a_impl
(self, cls: Cls)
mllm/compile/ir/rtti_kind_gen.py:113
↓ 1 callersMethodgen_base_impl
(self, cls: Cls)
mllm/compile/ir/rtti_kind_gen.py:105
↓ 1 callersMethodgen_impl
(self, cls: Cls)
mllm/compile/ir/rtti_kind_gen.py:121
↓ 1 callersMethodgeneralFree
mllm/backends/cpu/CPUAllocator.cpp:62
↓ 1 callersMethodgenerate
* Generate audio codes in streaming or non-streaming setting */
mllm/models/minicpm_o2_6/modeling_chattts.hpp:286
↓ 1 callersFunctiongenerate_clangd
()
mllm-kernel/mllm_kernel/__main__.py:1
↓ 1 callersFunctiongenerate_md5
(input_str: str)
mllm/backends/opencl/kernels/gen_opencl_kernel_cpp_wrap.py:7
↓ 1 callersMethodgenerate_next
mllm/models/minicpm_o2_6/streaming_generation.cpp:16
↓ 1 callersMethodgenerate_next_chunk
* @brief Generate next chunk of tokens */
mllm/models/minicpm_o2_6/llm_chunk_generation.hpp:220
↓ 1 callersFunctiongenerate_op_files
(op_name, out_dir="./aops")
mllm/core/gen_op.py:70
↓ 1 callersMethodgetAudioPlaceholder
mllm/models/minicpm_o2_6/audio_preprocessor_minicpmo.hpp:228
↓ 1 callersMethodgetBuildInfo
mllm/backends/opencl/vendors/OpenCL-Headers/CL/opencl.hpp:7176
↓ 1 callersMethodgetCacheInputOutputTensor
mllm/compile/ir/Node.cpp:268
↓ 1 callersFunctiongetConvTemplate
* Get a conversation template */
mllm/models/deepseek_ocr/conversation_preprocess.hpp:252
↓ 1 callersMethodgetCpuOpThreads
mllm/engine/Context.cpp:163
↓ 1 callersMethodgetCustomOpTypeName
mllm/backends/base/PluginInterface.hpp:24
↓ 1 callersMethodgetFreedTensor
mllm/compile/ir/tensor/Op.cpp:98
↓ 1 callersMethodgetGpuType
mllm/backends/opencl/runtime/OpenCLRuntime.cpp:94
↓ 1 callersMethodgetInputsConstant
mllm/core/BaseOp.hpp:56
↓ 1 callersMethodgetKCacheBuffer
mllm/nn/lmcache/StaticCache.hpp:59
↓ 1 callersMethodgetKind
mllm/compile/ir/Node.hpp:60
↓ 1 callersMethodgetLastHiddenStates
mllm/models/minicpm_o2_6/llm_chunk_generation.hpp:142
↓ 1 callersMethodgetName
mllm/core/BaseOp.cpp:16
↓ 1 callersMethodgetParamFile
mllm/backends/qnn/aot/passes/AOTCompileContext.cpp:26
↓ 1 callersFunctiongetPlatformVersion
mllm/backends/opencl/vendors/OpenCL-Headers/CL/opencl.hpp:2164
↓ 1 callersMethodgetPrompt
* Get the prompt for generation */
mllm/models/deepseek_ocr/conversation_preprocess.hpp:63
↓ 1 callersMethodgetRandomSeed
mllm/engine/Context.cpp:125
↓ 1 callersFunctiongetRandomState
mllm/mllm.cpp:72
↓ 1 callersMethodgetRegisteredTensor
mllm/compile/ir/tensor/Op.cpp:58
↓ 1 callersMethodgetUniqueModuleName
mllm/compile/ir/Node.cpp:232
↓ 1 callersMethodgetVCacheBuffer
mllm/nn/lmcache/StaticCache.hpp:61
↓ 1 callersFunctiongetVersion
Extracts version number with major in the upper 16 bits, minor in the lower 16
mllm/backends/opencl/vendors/OpenCL-Headers/CL/opencl.hpp:2145
↓ 1 callersMethodgetWorkGroupInfo
mllm/backends/opencl/vendors/OpenCL-Headers/CL/opencl.hpp:6319
↓ 1 callersFunctionget_clip_timepoints
mllm/preprocessor/audio/Audio.cpp:396
↓ 1 callersMethodget_index
mllm/utils/Enumerate.hpp:20
↓ 1 callersFunctionget_jit_kernel_registry
Get a shallow copy of all registered JIT kernels.
mllm-kernel/mllm_kernel/jit_utils/compile.py:219
↓ 1 callersFunctionget_qvals_range
mllm/backends/cpu/kernels/arm/quantize/bitspack/bitspack.cpp:26
↓ 1 callersFunctionget_response
(id: str)
pymllm/service/rr_process.py:22
↓ 1 callersFunctionget_scale
mllm/backends/cpu/kernels/arm/quantize/bitspack/bitspack.cpp:36
↓ 1 callersFunctionget_scale_and_zero
mllm/backends/cpu/kernels/arm/quantize/bitspack/bitspack.cpp:42
↓ 1 callersFunctionget_sinc_resample_kernel
mllm/preprocessor/audio/Audio.cpp:182
↓ 1 callersMethodget_slice_image_placeholder
mllm/models/minicpm_o2_6/image_preprocessor_minicpmo.hpp:185
↓ 1 callersMethodget_value
mllm/utils/Enumerate.hpp:21
↓ 1 callersMethodget_value
mllm-kernel/include/mllm_kernel/tensor.hpp:178
↓ 1 callersMethodgraphExecute
mllm/backends/qnn/QNNBackend.cpp:646
↓ 1 callersMethodhandleFlag
mllm/utils/Argparse.hpp:92
↓ 1 callersFunctionhasBF16
mllm/utils/CPUArchHelper.hpp:193
↓ 1 callersFunctionhasDotProd
mllm/utils/CPUArchHelper.hpp:217
↓ 1 callersFunctionhasFMA
mllm/utils/CPUArchHelper.hpp:303
↓ 1 callersFunctionhasFP16
mllm/utils/CPUArchHelper.hpp:187
↓ 1 callersFunctionhasSME
mllm/utils/CPUArchHelper.hpp:205
↓ 1 callersFunctionhasSVE
mllm/utils/CPUArchHelper.hpp:199
↓ 1 callersMethodhasSymbolAttr
mllm/compile/ir/builtin/Interface.hpp:21
↓ 1 callersMethodhaveToken
mllm/compile/symbolic_expr/Parser.cpp:46
↓ 1 callersMethodhintsPrefetch
mllm/engine/prefix_cache/ZenFS.cpp:521
↓ 1 callersMethodhintsPurge
mllm/engine/prefix_cache/ZenFS.cpp:542
↓ 1 callersFunctionhvx_add_af
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/LLaMAAdd.cpp:90
↓ 1 callersFunctionhvx_mul_af
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/LLaMAMul.cpp:89
↓ 1 callersFunctionhvx_mul_ahf
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/LLaMAMul.cpp:152
↓ 1 callersFunctionhvx_qlayernorm_af
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/QLayerNorm.cpp:89
↓ 1 callersFunctionhvx_rmsnorm_af
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/RMSNorm.cpp:90
↓ 1 callersFunctionhvx_rmsnorm_auint8
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/RMSNorm.cpp:216
↓ 1 callersFunctionhvx_rope_af
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/RoPE.cpp:95
↓ 1 callersFunctionhvx_rope_ahf
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/RoPE.cpp:397
↓ 1 callersFunctionhvx_rope_uint8_af
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/RoPE.cpp:189
↓ 1 callersFunctionhvx_rope_uint8_ahf
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/RoPE.cpp:285
↓ 1 callersFunctionhvx_silu_af
* @brief Polynomial approximation of x/(exp(-x)+1.0) function. * @param[in] input Input array of elements in IEEE 32-bit floating-point for
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/SiLU.cpp:284
↓ 1 callersFunctionhvx_silu_ahf
* @brief Polynomial approximation of 1.0/(exp(-x)+1.0) function. * @param[in] input Input array of elements in IEEE 16-bit floating-point f
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/SiLU.cpp:807
↓ 1 callersFunctionhvx_supersilu_ahf
mllm/backends/qnn/custom-op-package/LLaMAPackage/src/ops/LLaMASuperSiLU.cpp:289
← previousnext →1,301–1,400 of 5,971, ranked by callers