InferenceRequest
InferenceRequest(const RequestId &reqId)
InferenceRequest() = delete
Status AddOriginalInput(const LLM_ENGINE_DataType datatype, const int64_t *shape, const uint64_t dim_count, Input **input)
Status AddOriginalInput(const std::string &name, const LLM_ENGINE_DataType datatype, const int64_t *shape, const uint64_t dim_count, Input **input)
Status RemoveOriginalInput(const std::string &name)
uint32_t MaxOutputLen() const
bool SetMaxOutputLen(uint32_t max_output_len)
RequestId &GetRequestId()
SamplingParams GetSamplingParams() const
void SetSamplingParams(SamplingParams samplingParams)
void SetSendResponseCallback(const SendResponseCallback &callback)
bool HasSampling()
void SetInputText(std::string &text)
std::string &GetInputText()
bool IsInputText()
std::shared_ptr<InferenceRequestInner> GetRequestInner() const
父主题:
类参考