Dual GEMM Plugin

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

SwiGLU gate/up dual GEMM: H = silu(X @ Wg^T) * (X @ Wu^T) in one CuTe DSL kernel (Blackwell datacenter / Thor).

Inputs: [0] activation X, FP16, […, K] [1] packed gate/up weight, FP16, [2N, K] in the dual_gemm_blackwell layout (pack_gate_up_weights in kernelSrcs/gemm_cutedsl/dual_gemm_blackwell.py) Output: [0] H, FP16, […, N] Attributes: inter_size (N), hidden_size (K), activation (0 = SiLU).

Public Functions

DualGemmPlugin(

std::string const &name,

int32_t interSize,

int32_t hiddenSize,

int32_t activation

)

DualGemmPlugin(

std::string const &name,

nvinfer1::PluginFieldCollection const *fc

)

DualGemmPlugin() = delete

DualGemmPlugin(DualGemmPlugin const&) = delete

DualGemmPlugin &operator=(DualGemmPlugin const&) = delete

~DualGemmPlugin() 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

class DualGemmPluginCreator : public nvinfer1::IPluginCreatorV3One

Public Functions

DualGemmPluginCreator()

~DualGemmPluginCreator() 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