Sparse Attention Plugin

class SparseAttentionPlugin : public nvinfer1::IPluginV3, public nvinfer1::IPluginV3OneCore, public nvinfer1::IPluginV3OneBuild, public nvinfer1::IPluginV3OneRuntime

Noncausal block-sparse attention over one packed [prefix | suffix] BF16 sequence. ! ! Inputs are Q, K, and V [sequence, heads, headSize] and a suffix-row carrier whose first dimension is the number of block-sparse suffix rows; its data is never read. The output has the shape and type of Q. See VideoSparseAttentionRunner for the routing.

Public Functions

explicit SparseAttentionPlugin(std::string const &name)

~SparseAttentionPlugin() noexcept override = default

nvinfer1::IPluginCapability *getCapabilityInterface(

nvinfer1::PluginCapabilityType type

) noexcept override

nvinfer1::IPluginV3 *clone() noexcept override

char const *getPluginName() const noexcept override

char const *getPluginVersion() const noexcept override

char const *getPluginNamespace() const noexcept override

void setPluginNamespace(char const *pluginNamespace) noexcept

int32_t getNbOutputs() const noexcept override

int32_t getOutputDataTypes(

nvinfer1::DataType *outputTypes,

int32_t nbOutputs,

nvinfer1::DataType const *inputTypes,

int32_t nbInputs

) const noexcept override

int32_t getOutputShapes(

nvinfer1::DimsExprs const *inputs,

int32_t nbInputs,

nvinfer1::DimsExprs const *shapeInputs,

int32_t nbShapeInputs,

nvinfer1::DimsExprs *outputs,

int32_t nbOutputs,

nvinfer1::IExprBuilder &exprBuilder

) noexcept override

bool supportsFormatCombination(

int32_t pos,

nvinfer1::DynamicPluginTensorDesc const *inOut,

int32_t nbInputs,

int32_t nbOutputs

) noexcept override

int32_t configurePlugin(

nvinfer1::DynamicPluginTensorDesc const *inputs,

int32_t nbInputs,

nvinfer1::DynamicPluginTensorDesc const *outputs,

int32_t nbOutputs

) noexcept override

size_t getWorkspaceSize(

nvinfer1::DynamicPluginTensorDesc const *inputs,

int32_t nbInputs,

nvinfer1::DynamicPluginTensorDesc const *outputs,

int32_t nbOutputs

) const noexcept override

int32_t enqueue(

nvinfer1::PluginTensorDesc const *inputDesc,

nvinfer1::PluginTensorDesc const *outputDesc,

void const *const *inputs,

void *const *outputs,

void *workspace,

cudaStream_t stream

) noexcept override

int32_t onShapeChange(

nvinfer1::PluginTensorDesc const *inputs,

int32_t nbInputs,

nvinfer1::PluginTensorDesc const *outputs,

int32_t nbOutputs

) noexcept override

nvinfer1::IPluginV3 *attachToContext(

nvinfer1::IPluginResourceContext *context

) noexcept override

nvinfer1::PluginFieldCollection const *getFieldsToSerialize(

) noexcept override

class SparseAttentionPluginCreator : public nvinfer1::IPluginCreatorV3One

Public Functions

SparseAttentionPluginCreator() = default

~SparseAttentionPluginCreator() override = default

char const *getPluginName() const noexcept override

char const *getPluginVersion() const noexcept override

nvinfer1::PluginFieldCollection const *getFieldNames(

) noexcept override

char const *getPluginNamespace() const noexcept override

void setPluginNamespace(char const *pluginNamespace) noexcept

nvinfer1::IPluginV3 *createPlugin(

char const *name,

nvinfer1::PluginFieldCollection const *fields,

nvinfer1::TensorRTPhase phase

) noexcept override