Block Diffusion Decoder#

class BlockDiffusionDecoder : public trt_edgellm::rt::DecodingStrategy#

Public Functions

explicit BlockDiffusionDecoder(
DecodingRuntimeContext &runtime,
std::filesystem::path const &engineDir,
cudaStream_t stream
)#
inline virtual DecodingStrategyKind kind() const noexcept override#
inline virtual char const *name() const noexcept override#
inline virtual bool isSpeculative() const noexcept override#
inline virtual DecodingKvHeadroomPolicy kvHeadroom() const override#

KV headroom of the strategy’s decode rounds; the default is the vanilla one-token step.

inline virtual DecodingTokenStateContract tokenStateContract(
) const noexcept override#
virtual bool decodeStep(DecodingInferenceContext &context) override#
virtual bool captureCudaGraphs(cudaStream_t stream) override#
virtual int64_t getRequiredContextMemorySize(
) const noexcept override#
virtual void setContextMemory(Tensor &memory) override#
inline virtual void resetForNewSequences(
Tensor&,
cudaStream_t
) override#
inline virtual void onBatchEvict(
std::vector<int32_t> const&,
int32_t,
int32_t,
Tensor&,
cudaStream_t
) override#