Skip to main content

Module ffi

Module ffi

Expand description

Re-export of whole mnn-sys

Modules§

SessionMode
cpp

Structs§

Backend
CString
Interpreter
MNNBackendConfig
MNNScheduleConfig
MemoryMode
PowerMode
PrecisionMode
Session
Tensor
TensorInfo
TensorInfoArray
TensorShape
__fsid_t
halide_buffer_t: \file
halide_device_interface_impl_t: An opaque struct containing per-GPU API implementations of the device functions.
halide_device_interface_t: Each GPU API provides a halide_device_interface_t struct pointing to the code that manages device allocations. You can access these functions directly from the struct member function pointers, or by calling the functions declared below. Note that the global functions are not available when using Halide as a JIT compiler. If you are using raw halide_buffer_t in that context you must use the function pointers in the device_interface struct.
halide_dimension_t
halide_type_t: A runtime tag for a type in the halide type system. Can be ints, unsigned ints, or floats of various bit-widths (the ‘bits’ field). Can also be vectors of the same (by setting the ‘lanes’ field to something larger than one). This struct should be exactly 32-bits in size.
max_align_t

Enums§

DimensionType
ErrorCode
HandleDataType
MNNForwardType
MNNGpuMode
MapType
RuntimeStatus: acquire runtime status by Runtime::getCurrentStatus with following keys,
halide_type_code_t: Types in the halide type system. They can be ints, unsigned ints, or floats (of various bit-widths), or a handle (which is always 64-bits). Note that the int/uint/float values do not imply a specific bit width (the bit width is expected to be encoded in a separate value).

Constants§

Traits§

HalideType
MaybeDebug

Functions§

Interpreter_bizCode^⚠
Interpreter_createFromBuffer^⚠: @brief create net from buffer. @param buffer given data buffer. @param size size of data buffer. @return created net if success, NULL otherwise.
Interpreter_createFromFile^⚠: @brief create net from file. @param file given file. @return created net if success, NULL otherwise.
Interpreter_createMultiPathSession^⚠
Interpreter_createSession^⚠
Interpreter_destroy^⚠
Interpreter_getBackend^⚠
Interpreter_getModelVersion^⚠
Interpreter_getSessionInfo^⚠
Interpreter_getSessionInput^⚠
Interpreter_getSessionInputAll^⚠
Interpreter_getSessionOutput^⚠
Interpreter_getSessionOutputAll^⚠
Interpreter_releaseModel^⚠
Interpreter_releaseSession^⚠
Interpreter_resizeSession^⚠
Interpreter_resizeSessionWithFlag^⚠
Interpreter_resizeTensor^⚠
Interpreter_resizeTensorByNCHW^⚠
Interpreter_runSession^⚠
Interpreter_runSessionWithCallBackInfo^⚠
Interpreter_setCacheFile^⚠
Interpreter_setExternalFile^⚠
Interpreter_setSessionHint^⚠
Interpreter_setSessionMode^⚠
Interpreter_updateCacheFile^⚠
Interpreter_updateSessionToModel^⚠
Interpreter_uuid^⚠
OperatorInfo_flops^⚠
OperatorInfo_name^⚠
OperatorInfo_type^⚠
Session_destroy^⚠
Session_hasAsyncWork^⚠
Tensor_batch^⚠
Tensor_buffer^⚠
Tensor_buffer_mut^⚠
Tensor_channel^⚠
Tensor_clone^⚠
Tensor_copyFromHostTensor^⚠
Tensor_copyToHostTensor^⚠
Tensor_create^⚠
Tensor_createDevice^⚠
Tensor_createFromTensor^⚠
Tensor_createHostTensorFromDevice^⚠
Tensor_createWith^⚠
Tensor_destroy^⚠
Tensor_deviceId^⚠
Tensor_dimensions^⚠
Tensor_elementSize^⚠
Tensor_getDeviceInfo^⚠
Tensor_getDimensionType^⚠
Tensor_getType^⚠
Tensor_height^⚠
Tensor_host^⚠
Tensor_host_mut^⚠
Tensor_isTypeOf^⚠
Tensor_length^⚠
Tensor_map^⚠
Tensor_print^⚠
Tensor_printShape^⚠
Tensor_setDevicePtr^⚠
Tensor_setLength^⚠
Tensor_setStride^⚠
Tensor_shape^⚠
Tensor_size^⚠
Tensor_stride^⚠
Tensor_unmap^⚠
Tensor_usize^⚠
Tensor_wait^⚠
Tensor_width^⚠
createCString^⚠
createTensorInfoArray^⚠
destroyCString^⚠
destroyTensorInfoArray^⚠
getTensorInfoArray^⚠
getVersion^⚠: @brief get mnn version info. @return mnn version string.
halide_type_of
mnnbc_clone^⚠
mnnbc_create^⚠
mnnbc_destroy^⚠
mnnbc_get_memory_mode^⚠
mnnbc_get_power_mode^⚠
mnnbc_get_precision_mode^⚠
mnnbc_reset^⚠
mnnbc_set_flags^⚠
mnnbc_set_memory_mode^⚠
mnnbc_set_power_mode^⚠
mnnbc_set_precision_mode^⚠
mnnbc_set_shared_context^⚠
mnnsc_clone^⚠
mnnsc_create^⚠
mnnsc_destroy^⚠
mnnsc_get_backup_type^⚠
mnnsc_get_type^⚠
mnnsc_set_backend_config^⚠
mnnsc_set_backup_type^⚠
mnnsc_set_mode^⚠
mnnsc_set_num_threads^⚠
mnnsc_set_save_tensors^⚠
mnnsc_set_type^⚠
modelPrintIO^⚠

Type Aliases§