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#
-
virtual bool decodeStep(DecodingInferenceContext &context) override#
-
virtual bool captureCudaGraphs(cudaStream_t stream) override#
- virtual int64_t getRequiredContextMemorySize(
- inline virtual bool hasSystemPromptKVCache(
- SystemPromptCacheKey const&
- inline virtual void restoreSystemPromptKVCache(
- SystemPromptCacheKey const&,
- int32_t,
- cudaStream_t
- inline virtual bool runSystemPromptPrefill( ) override#
- inline virtual void saveSystemPromptKVCache(
- SystemPromptCacheKey const&,
- std::string const&,
- std::vector<tokenizer::Rank> const&,
- int32_t,
- cudaStream_t