model_variant_handle.h Source File#
|
SDK qb Runtime Library v1.4
MCS001-KR
|
model_variant_handle.h
Go to the documentation of this file.
Handle to a specific variant of a loaded model.
Definition model_variant_handle.h:35
Represents a model input or output tensor that can reside either on the host (CPU) or on the NPU.
Definition npu_data.h:51
StatusCode repositionOutputs(const std::vector< Buffer > &output_buf, std::vector< std::vector< float > > &output, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
const std::vector< std::vector< int64_t > > & getModelOutputShape() const
Returns the output shape for this model variant.
std::vector< std::vector< Buffer > > acquireOutputBuffers(int batch_size, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
StatusCode releaseBuffer(std::vector< Buffer > &buffer) const
Acquires an NPUData for this variant's input at the given index.
NPUData acquireOutputNPUData(const std::vector< int64_t > &shape, int idx, bool upload, DataType dtype, StatusCode &sc) const
Acquires an NPUData for this variant's output at the given index.
StatusCode repositionInputs(const std::vector< float * > &input, std::vector< Buffer > &input_buf, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
StatusCode repositionInputs(const std::vector< uint8_t * > &input, std::vector< Buffer > &input_buf, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
const std::vector< BufferInfo > & getOutputBufferInfo() const
Returns the output buffer information for this variant.
std::vector< Scale > getInputScale() const
Returns the input quantization scale(s) for this variant.
std::vector< Scale > getOutputScale() const
Returns the output quantization scale(s) for this variant.
StatusCode repositionOutputs(const std::vector< std::vector< Buffer > > &output_buf, std::vector< std::vector< float > > &output, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
StatusCode repositionOutputs(const std::vector< Buffer > &output_buf, std::vector< float * > &output, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
DataType getModelOutputDataType() const
Returns a data type for model outputs.
StatusCode releaseBuffers(std::vector< std::vector< Buffer > > &buffers) const
Acquires an NPUData for this variant's input at the given index.
DataType getModelInputDataType() const
Returns a data type for model inputs.
const std::vector< BufferInfo > & getInputBufferInfo() const
Returns the input buffer information for this variant.
StatusCode repositionInputs(const std::vector< float * > &input, std::vector< std::vector< Buffer > > &input_buf, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
const std::vector< std::vector< int64_t > > & getModelInputShape() const
Returns the input shape for this model variant.
StatusCode repositionOutputs(const std::vector< std::vector< Buffer > > &output_buf, std::vector< float * > &output, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
int getVariantIdx() const
Returns the index of this model variant.
std::vector< std::vector< Buffer > > acquireInputBuffers(int batch_size, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
std::vector< Buffer > acquireInputBuffer(const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
NPUData acquireInputNPUData(const std::vector< int64_t > &shape, int idx, bool upload, DataType dtype, StatusCode &sc) const
Acquires an NPUData for this variant's input at the given index.
std::vector< Buffer > acquireOutputBuffer(const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
StatusCode repositionInputs(const std::vector< uint8_t * > &input, std::vector< std::vector< Buffer > > &input_buf, const std::vector< std::vector< int > > &seqlens={}) const
Acquires an NPUData for this variant's input at the given index.
Generated by