InferenceEngine
InferenceEngine()
Status Init(const SendResponseCallback &callback = nullptr, const std::string &configPath = "")
Status GetRequestBlockQuotas(uint64_t *remainBlocks, uint64_t *remainPrefillSlots, uint64_t *remainPrefill)
Status Forward(std::shared_ptr<InferenceRequest> &request, bool validRequest = false)
Status GetProcessingRequest(uint64_t *num)
Status ControlRequest(const RequestId &requestId, Operation operation)
Status Finalize()
~InferenceEngine()
Status GetMaxBatchSize(uint64_t *batchSize)
父主题:
类参考