Defined in File triton_inference.hpp
Base Type
public morpheus::ITritonClient(Class ITritonClient)
-
class HttpTritonClient : public morpheus::ITritonClient
-
Public Functions
- HttpTritonClient(std::string server_url)
- virtual triton::client::Error is_server_live(bool *live) override
Checks if Triton Server is live using HTTP protocal.
- virtual triton::client::Error is_server_ready(bool *ready) override
Checks if Triton Server is ready using HTTP protocal.
- virtual triton::client::Error is_model_ready(bool *ready, std::string &model_name) override
Checks if the given model is ready using HTTP protocal.
- virtual triton::client::Error model_config(std::string *model_config, std::string &model_name) override
Gets the config for the given model using HTTP protocal.
- virtual triton::client::Error model_metadata(std::string *model_metadata, std::string &model_name) override
Gets metadata for the given model using HTTP protocal.
- virtual triton::client::Error async_infer(triton::client::InferenceServerHttpClient::OnCompleteFn callback, const triton::client::InferOptions &options, const std::vector<TritonInferInput> &inputs, const std::vector<TritonInferRequestedOutput> &outputs) override
Runs Triton Server inference given the model options, inputs, and outputs, using HTTP protocal.