Nvfp4 A16 GEMM Plugin V2

class Nvfp4A16GemmPluginV2 : public nvinfer1::IPluginV3, public nvinfer1::IPluginV3OneCore, public nvinfer1::IPluginV3OneBuild, public nvinfer1::IPluginV3OneRuntime

SM110-only dense NVFP4-A16 plugin using one common tiled weight layout for decode and prefill.

Public Functions

Nvfp4A16GemmPluginV2(

std::string const &name,

int32_t gemmN,

int32_t gemmK,

int32_t maxM,

int32_t layout,

int32_t backend

)

Nvfp4A16GemmPluginV2(

std::string const &name,

nvinfer1::PluginFieldCollection const *fc

)

Nvfp4A16GemmPluginV2() = delete

Nvfp4A16GemmPluginV2(Nvfp4A16GemmPluginV2 const&) = delete

Nvfp4A16GemmPluginV2 &operator=(Nvfp4A16GemmPluginV2 const&) = delete

~Nvfp4A16GemmPluginV2() 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

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 *in,

int32_t nbInputs,

nvinfer1::DynamicPluginTensorDesc const *out,

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 *in,

int32_t nbInputs,

nvinfer1::PluginTensorDesc const *out,

int32_t nbOutputs

) noexcept override

nvinfer1::IPluginV3 *attachToContext(

nvinfer1::IPluginResourceContext *context

) noexcept override

nvinfer1::PluginFieldCollection const *getFieldsToSerialize(

) noexcept override

void setPluginNamespace(char const *pluginNamespace) noexcept

bool hasSerializedGemvJitBundle() const noexcept

void loadSerializedGemvJitBundle()

class Nvfp4A16GemmPluginV2Creator : public nvinfer1::IPluginCreatorV3One

Creator registered as Nvfp4A16GemmPlugin version 2; version 1 remains the Marlin implementation.

Public Functions

Nvfp4A16GemmPluginV2Creator()

~Nvfp4A16GemmPluginV2Creator() 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 *fc,

nvinfer1::TensorRTPhase phase

) noexcept override