+ * The TRITONSERVER_Error error codes */ +/** enum TRITONSERVER_Error_Code */ +public static final int + TRITONSERVER_ERROR_UNKNOWN = 0, + TRITONSERVER_ERROR_INTERNAL = 1, + TRITONSERVER_ERROR_NOT_FOUND = 2, + TRITONSERVER_ERROR_INVALID_ARG = 3, + TRITONSERVER_ERROR_UNAVAILABLE = 4, + TRITONSERVER_ERROR_UNSUPPORTED = 5, + TRITONSERVER_ERROR_ALREADY_EXISTS = 6; + +/** Create a new error object. The caller takes ownership of the + * TRITONSERVER_Error object and must call TRITONSERVER_ErrorDelete to + * release the object. + * + * @param code The error code. + * @param msg The error message. + * @return A new TRITONSERVER_Error object. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_ErrorNew( + @Cast("TRITONSERVER_Error_Code") int code, String msg); +public static native TRITONSERVER_Error TRITONSERVER_ErrorNew( + @Cast("TRITONSERVER_Error_Code") int code, @Cast("const char*") BytePointer msg); + +/** Delete an error object. + * + * @param error The error object. */ + +/// +public static native void TRITONSERVER_ErrorDelete(TRITONSERVER_Error error); + +/** Get the error code. + * + * @param error The error object. + * @return The error code. */ + +/// +public static native @Cast("TRITONSERVER_Error_Code") int TRITONSERVER_ErrorCode(TRITONSERVER_Error error); + +/** Get the string representation of an error code. The returned + * string is not owned by the caller and so should not be modified or + * freed. The lifetime of the returned string extends only as long as + * 'error' and must not be accessed once 'error' is deleted. + * + * @param error The error object. + * @return The string representation of the error code. */ + +/// +public static native String TRITONSERVER_ErrorCodeString( + TRITONSERVER_Error error); + +/** Get the error message. The returned string is not owned by the + * caller and so should not be modified or freed. The lifetime of the + * returned string extends only as long as 'error' and must not be + * accessed once 'error' is deleted. + * + * @param error The error object. + * @return The error message. */ + +/// +/// +/// +public static native String TRITONSERVER_ErrorMessage( + TRITONSERVER_Error error); +// Targeting ../tritonserver/TRITONSERVER_ResponseAllocatorAllocFn_t.java + + +// Targeting ../tritonserver/TRITONSERVER_ResponseAllocatorReleaseFn_t.java + + +// Targeting ../tritonserver/TRITONSERVER_ResponseAllocatorStartFn_t.java + + + +/** Create a new response allocator object. + * + * The response allocator object is used by Triton to allocate + * buffers to hold the output tensors in inference responses. Most + * models generate a single response for each inference request + * (TRITONSERVER_TXN_ONE_TO_ONE). For these models the order of + * callbacks will be: + * + * TRITONSERVER_ServerInferAsync called + * - start_fn : optional (and typically not required) + * - alloc_fn : called once for each output tensor in response + * TRITONSERVER_InferenceResponseDelete called + * - release_fn: called once for each output tensor in response + * + * For models that generate multiple responses for each inference + * request (TRITONSERVER_TXN_DECOUPLED), the start_fn callback can be + * used to determine sets of alloc_fn callbacks that belong to the + * same response: + * + * TRITONSERVER_ServerInferAsync called + * - start_fn + * - alloc_fn : called once for each output tensor in response + * - start_fn + * - alloc_fn : called once for each output tensor in response + * ... + * For each response, TRITONSERVER_InferenceResponseDelete called + * - release_fn: called once for each output tensor in the response + * + * In all cases the start_fn, alloc_fn and release_fn callback + * functions must be thread-safe. Typically making these functions + * thread-safe does not require explicit locking. The recommended way + * to implement these functions is to have each inference request + * provide a 'response_allocator_userp' object that is unique to that + * request with TRITONSERVER_InferenceRequestSetResponseCallback. The + * callback functions then operate only on this unique state. Locking + * is required only when the callback function needs to access state + * that is shared across inference requests (for example, a common + * allocation pool). + * + * @param allocator Returns the new response allocator object. + * @param alloc_fn The function to call to allocate buffers for result + * tensors. + * @param release_fn The function to call when the server no longer + * holds a reference to an allocated buffer. + * @param start_fn The function to call to indicate that the + * subsequent 'alloc_fn' calls are for a new response. This callback + * is optional (use nullptr to indicate that it should not be + * invoked). +
+ * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_ResponseAllocatorNew( + @Cast("TRITONSERVER_ResponseAllocator**") PointerPointer allocator, + TRITONSERVER_ResponseAllocatorAllocFn_t alloc_fn, + TRITONSERVER_ResponseAllocatorReleaseFn_t release_fn, + TRITONSERVER_ResponseAllocatorStartFn_t start_fn); +public static native TRITONSERVER_Error TRITONSERVER_ResponseAllocatorNew( + @ByPtrPtr TRITONSERVER_ResponseAllocator allocator, + TRITONSERVER_ResponseAllocatorAllocFn_t alloc_fn, + TRITONSERVER_ResponseAllocatorReleaseFn_t release_fn, + TRITONSERVER_ResponseAllocatorStartFn_t start_fn); + +/** Delete a response allocator. + * + * @param allocator The response allocator object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +/// +/// +public static native TRITONSERVER_Error TRITONSERVER_ResponseAllocatorDelete( + TRITONSERVER_ResponseAllocator allocator); + +/** TRITONSERVER_Message + * + * Object representing a Triton Server message. + * +
+ * Create a new message object from serialized JSON string. + * + * @param message The message object. + * @param base The base of the serialized JSON. + * @param byte_size The size, in bytes, of the serialized message. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_MessageNewFromSerializedJson( + @Cast("TRITONSERVER_Message**") PointerPointer message, String base, @Cast("size_t") long byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MessageNewFromSerializedJson( + @ByPtrPtr TRITONSERVER_Message message, String base, @Cast("size_t") long byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MessageNewFromSerializedJson( + @ByPtrPtr TRITONSERVER_Message message, @Cast("const char*") BytePointer base, @Cast("size_t") long byte_size); + +/** Delete a message object. + * + * @param message The message object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_MessageDelete( + TRITONSERVER_Message message); + +/** Get the base and size of the buffer containing the serialized + * message in JSON format. The buffer is owned by the + * TRITONSERVER_Message object and should not be modified or freed by + * the caller. The lifetime of the buffer extends only as long as + * 'message' and must not be accessed once 'message' is deleted. + * + * @param message The message object. + * @param base Returns the base of the serialized message. + * @param byte_size Returns the size, in bytes, of the serialized + * message. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +/// +public static native TRITONSERVER_Error TRITONSERVER_MessageSerializeToJson( + TRITONSERVER_Message message, @Cast("const char**") PointerPointer base, @Cast("size_t*") SizeTPointer byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MessageSerializeToJson( + TRITONSERVER_Message message, @Cast("const char**") @ByPtrPtr BytePointer base, @Cast("size_t*") SizeTPointer byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MessageSerializeToJson( + TRITONSERVER_Message message, @Cast("const char**") @ByPtrPtr ByteBuffer base, @Cast("size_t*") SizeTPointer byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MessageSerializeToJson( + TRITONSERVER_Message message, @Cast("const char**") @ByPtrPtr byte[] base, @Cast("size_t*") SizeTPointer byte_size); + +/** TRITONSERVER_Metrics + * + * Object representing metrics. + * +
+ * Metric format types */ +/** enum TRITONSERVER_MetricFormat */ +public static final int + TRITONSERVER_METRIC_PROMETHEUS = 0; + +/** Delete a metrics object. + * + * @param metrics The metrics object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +/// +/// +public static native TRITONSERVER_Error TRITONSERVER_MetricsDelete( + TRITONSERVER_Metrics metrics); + +/** Get a buffer containing the metrics in the specified format. For + * each format the buffer contains the following: + * + * TRITONSERVER_METRIC_PROMETHEUS: 'base' points to a single multiline + * string (char*) that gives a text representation of the metrics in + * prometheus format. 'byte_size' returns the length of the string + * in bytes. + * + * The buffer is owned by the 'metrics' object and should not be + * modified or freed by the caller. The lifetime of the buffer + * extends only as long as 'metrics' and must not be accessed once + * 'metrics' is deleted. + * + * @param metrics The metrics object. + * @param format The format to use for the returned metrics. + * @param base Returns a pointer to the base of the formatted + * metrics, as described above. + * @param byte_size Returns the size, in bytes, of the formatted + * metrics. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +/// +public static native TRITONSERVER_Error TRITONSERVER_MetricsFormatted( + TRITONSERVER_Metrics metrics, @Cast("TRITONSERVER_MetricFormat") int format, + @Cast("const char**") PointerPointer base, @Cast("size_t*") SizeTPointer byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MetricsFormatted( + TRITONSERVER_Metrics metrics, @Cast("TRITONSERVER_MetricFormat") int format, + @Cast("const char**") @ByPtrPtr BytePointer base, @Cast("size_t*") SizeTPointer byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MetricsFormatted( + TRITONSERVER_Metrics metrics, @Cast("TRITONSERVER_MetricFormat") int format, + @Cast("const char**") @ByPtrPtr ByteBuffer base, @Cast("size_t*") SizeTPointer byte_size); +public static native TRITONSERVER_Error TRITONSERVER_MetricsFormatted( + TRITONSERVER_Metrics metrics, @Cast("TRITONSERVER_MetricFormat") int format, + @Cast("const char**") @ByPtrPtr byte[] base, @Cast("size_t*") SizeTPointer byte_size); + +/** TRITONSERVER_InferenceTrace + * + * Object that represents tracing for an inference request. + * +
+ * Trace levels */ +/** enum TRITONSERVER_InferenceTraceLevel */ +public static final int + TRITONSERVER_TRACE_LEVEL_DISABLED = 0, + TRITONSERVER_TRACE_LEVEL_MIN = 1, + TRITONSERVER_TRACE_LEVEL_MAX = 2; + +/** Get the string representation of a trace level. The returned + * string is not owned by the caller and so should not be modified or + * freed. + * + * @param level The trace level. + * @return The string representation of the trace level. */ +public static native String TRITONSERVER_InferenceTraceLevelString( + @Cast("TRITONSERVER_InferenceTraceLevel") int level); + +// Trace activities +/** enum TRITONSERVER_InferenceTraceActivity */ +public static final int + TRITONSERVER_TRACE_REQUEST_START = 0, + TRITONSERVER_TRACE_QUEUE_START = 1, + TRITONSERVER_TRACE_COMPUTE_START = 2, + TRITONSERVER_TRACE_COMPUTE_INPUT_END = 3, + TRITONSERVER_TRACE_COMPUTE_OUTPUT_START = 4, + TRITONSERVER_TRACE_COMPUTE_END = 5, + TRITONSERVER_TRACE_REQUEST_END = 6; + +/** Get the string representation of a trace activity. The returned + * string is not owned by the caller and so should not be modified or + * freed. + * + * @param activity The trace activity. + * @return The string representation of the trace activity. */ +public static native String TRITONSERVER_InferenceTraceActivityString( + @Cast("TRITONSERVER_InferenceTraceActivity") int activity); +// Targeting ../tritonserver/TRITONSERVER_InferenceTraceActivityFn_t.java + + +// Targeting ../tritonserver/TRITONSERVER_InferenceTraceReleaseFn_t.java + + + +/** Create a new inference trace object. The caller takes ownership of + * the TRITONSERVER_InferenceTrace object and must call + * TRITONSERVER_InferenceTraceDelete to release the object. + * + * The activity callback function will be called to report activity + * for 'trace' as well as for any child traces that are spawned by + * 'trace', and so the activity callback must check the trace object + * to determine specifically what activity is being reported. + * + * The release callback is called for both 'trace' and for any child + * traces spawned by 'trace'. + * + * @param trace Returns the new inference trace object. + * @param level The tracing level. + * @param parent_id The parent trace id for this trace. A value of 0 + * indicates that there is not parent trace. + * @param activity_fn The callback function where activity for the + * trace is reported. + * @param release_fn The callback function called when all activity + * is complete for the trace. + * @param trace_userp User-provided pointer that is delivered to + * the activity and release callback functions. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceNew( + @Cast("TRITONSERVER_InferenceTrace**") PointerPointer trace, @Cast("TRITONSERVER_InferenceTraceLevel") int level, + @Cast("uint64_t") long parent_id, TRITONSERVER_InferenceTraceActivityFn_t activity_fn, + TRITONSERVER_InferenceTraceReleaseFn_t release_fn, Pointer trace_userp); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceNew( + @ByPtrPtr TRITONSERVER_InferenceTrace trace, @Cast("TRITONSERVER_InferenceTraceLevel") int level, + @Cast("uint64_t") long parent_id, TRITONSERVER_InferenceTraceActivityFn_t activity_fn, + TRITONSERVER_InferenceTraceReleaseFn_t release_fn, Pointer trace_userp); + +/** Delete a trace object. + * + * @param trace The trace object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceDelete( + TRITONSERVER_InferenceTrace trace); + +/** Get the id associated with a trace. Every trace is assigned an id + * that is unique across all traces created for a Triton server. + * + * @param trace The trace. + * @param id Returns the id associated with the trace. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceId( + TRITONSERVER_InferenceTrace trace, @Cast("uint64_t*") LongPointer id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceId( + TRITONSERVER_InferenceTrace trace, @Cast("uint64_t*") LongBuffer id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceId( + TRITONSERVER_InferenceTrace trace, @Cast("uint64_t*") long[] id); + +/** Get the parent id associated with a trace. The parent id indicates + * a parent-child relationship between two traces. A parent id value + * of 0 indicates that there is no parent trace. + * + * @param trace The trace. + * @param id Returns the parent id associated with the trace. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceParentId( + TRITONSERVER_InferenceTrace trace, @Cast("uint64_t*") LongPointer parent_id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceParentId( + TRITONSERVER_InferenceTrace trace, @Cast("uint64_t*") LongBuffer parent_id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceParentId( + TRITONSERVER_InferenceTrace trace, @Cast("uint64_t*") long[] parent_id); + +/** Get the name of the model associated with a trace. The caller does + * not own the returned string and must not modify or delete it. The + * lifetime of the returned string extends only as long as 'trace'. + * + * @param trace The trace. + * @param model_name Returns the name of the model associated with + * the trace. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelName( + TRITONSERVER_InferenceTrace trace, @Cast("const char**") PointerPointer model_name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelName( + TRITONSERVER_InferenceTrace trace, @Cast("const char**") @ByPtrPtr BytePointer model_name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelName( + TRITONSERVER_InferenceTrace trace, @Cast("const char**") @ByPtrPtr ByteBuffer model_name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelName( + TRITONSERVER_InferenceTrace trace, @Cast("const char**") @ByPtrPtr byte[] model_name); + +/** Get the version of the model associated with a trace. + * + * @param trace The trace. + * @param model_version Returns the version of the model associated + * with the trace. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelVersion( + TRITONSERVER_InferenceTrace trace, @Cast("int64_t*") LongPointer model_version); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelVersion( + TRITONSERVER_InferenceTrace trace, @Cast("int64_t*") LongBuffer model_version); +public static native TRITONSERVER_Error TRITONSERVER_InferenceTraceModelVersion( + TRITONSERVER_InferenceTrace trace, @Cast("int64_t*") long[] model_version); + +/** TRITONSERVER_InferenceRequest + * + * Object representing an inference request. The inference request + * provides the meta-data and input tensor values needed for an + * inference and returns the inference result meta-data and output + * tensors. An inference request object can be modified and reused + * multiple times. + * +
+ * Inference request flags. The enum values must be power-of-2 values. */ +/** enum TRITONSERVER_RequestFlag */ +public static final int + TRITONSERVER_REQUEST_FLAG_SEQUENCE_START = 1, + TRITONSERVER_REQUEST_FLAG_SEQUENCE_END = 2; + +/** Inference request release flags. The enum values must be + * power-of-2 values. */ +/** enum TRITONSERVER_RequestReleaseFlag */ +public static final int + TRITONSERVER_REQUEST_RELEASE_ALL = 1; + +/** Inference response complete flags. The enum values must be + * power-of-2 values. */ +/** enum TRITONSERVER_ResponseCompleteFlag */ +public static final int + TRITONSERVER_RESPONSE_COMPLETE_FINAL = 1; +// Targeting ../tritonserver/TRITONSERVER_InferenceRequestReleaseFn_t.java + + +// Targeting ../tritonserver/TRITONSERVER_InferenceResponseCompleteFn_t.java + + + +/** Create a new inference request object. + * + * @param inference_request Returns the new request object. + * @param server the inference server object. + * @param model_name The name of the model to use for the request. + * @param model_version The version of the model to use for the + * request. If -1 then the server will choose a version based on the + * model's policy. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestNew( + @Cast("TRITONSERVER_InferenceRequest**") PointerPointer inference_request, + TRITONSERVER_Server server, String model_name, + @Cast("const int64_t") long model_version); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestNew( + @ByPtrPtr TRITONSERVER_InferenceRequest inference_request, + TRITONSERVER_Server server, String model_name, + @Cast("const int64_t") long model_version); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestNew( + @ByPtrPtr TRITONSERVER_InferenceRequest inference_request, + TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name, + @Cast("const int64_t") long model_version); + +/** Delete an inference request object. + * + * @param inference_request The request object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestDelete( + TRITONSERVER_InferenceRequest inference_request); + +/** Get the ID for a request. The returned ID is owned by + * 'inference_request' and must not be modified or freed by the + * caller. + * + * @param inference_request The request object. + * @param id Returns the ID. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestId( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char**") PointerPointer id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestId( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char**") @ByPtrPtr BytePointer id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestId( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char**") @ByPtrPtr ByteBuffer id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestId( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char**") @ByPtrPtr byte[] id); + +/** Set the ID for a request. + * + * @param inference_request The request object. + * @param id The ID. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetId( + TRITONSERVER_InferenceRequest inference_request, String id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetId( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer id); + +/** Get the flag(s) associated with a request. On return 'flags' holds + * a bitwise-or of all flag values, see TRITONSERVER_RequestFlag for + * available flags. + * + * @param inference_request The request object. + * @param flags Returns the flags. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestFlags( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t*") IntPointer flags); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestFlags( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t*") IntBuffer flags); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestFlags( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t*") int[] flags); + +/** Set the flag(s) associated with a request. 'flags' should holds a + * bitwise-or of all flag values, see TRITONSERVER_RequestFlag for + * available flags. + * + * @param inference_request The request object. + * @param flags The flags. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetFlags( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t") int flags); + +/** Get the correlation ID of the inference request. Default is 0, + * which indictes that the request has no correlation ID. The + * correlation ID is used to indicate two or more inference request + * are related to each other. How this relationship is handled by the + * inference server is determined by the model's scheduling + * policy. + * + * @param inference_request The request object. + * @param correlation_id Returns the correlation ID. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestCorrelationId( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t*") LongPointer correlation_id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestCorrelationId( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t*") LongBuffer correlation_id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestCorrelationId( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t*") long[] correlation_id); + +/** Set the correlation ID of the inference request. Default is 0, which + * indictes that the request has no correlation ID. The correlation ID + * is used to indicate two or more inference request are related to + * each other. How this relationship is handled by the inference + * server is determined by the model's scheduling policy. + * + * @param inference_request The request object. + * @param correlation_id The correlation ID. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetCorrelationId( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t") long correlation_id); + +/** Get the priority for a request. The default is 0 indicating that + * the request does not specify a priority and so will use the + * model's default priority. + * + * @param inference_request The request object. + * @param priority Returns the priority level. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestPriority( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t*") IntPointer priority); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestPriority( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t*") IntBuffer priority); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestPriority( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t*") int[] priority); + +/** Set the priority for a request. The default is 0 indicating that + * the request does not specify a priority and so will use the + * model's default priority. + * + * @param inference_request The request object. + * @param priority The priority level. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetPriority( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint32_t") int priority); + +/** Get the timeout for a request, in microseconds. The default is 0 + * which indicates that the request has no timeout. + * + * @param inference_request The request object. + * @param timeout_us Returns the timeout, in microseconds. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestTimeoutMicroseconds( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t*") LongPointer timeout_us); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestTimeoutMicroseconds( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t*") LongBuffer timeout_us); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestTimeoutMicroseconds( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t*") long[] timeout_us); + +/** Set the timeout for a request, in microseconds. The default is 0 + * which indicates that the request has no timeout. + * + * @param inference_request The request object. + * @param timeout_us The timeout, in microseconds. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetTimeoutMicroseconds( + TRITONSERVER_InferenceRequest inference_request, @Cast("uint64_t") long timeout_us); + +/** Add an input to a request. + * + * @param inference_request The request object. + * @param name The name of the input. + * @param datatype The type of the input. Valid type names are BOOL, + * UINT8, UINT16, UINT32, UINT64, INT8, INT16, INT32, INT64, FP16, + * FP32, FP64, and BYTES. + * @param shape The shape of the input. + * @param dim_count The number of dimensions of 'shape'. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddInput( + TRITONSERVER_InferenceRequest inference_request, String name, + @Cast("const TRITONSERVER_DataType") int datatype, @Cast("const int64_t*") LongPointer shape, + @Cast("uint64_t") long dim_count); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddInput( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name, + @Cast("const TRITONSERVER_DataType") int datatype, @Cast("const int64_t*") LongBuffer shape, + @Cast("uint64_t") long dim_count); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddInput( + TRITONSERVER_InferenceRequest inference_request, String name, + @Cast("const TRITONSERVER_DataType") int datatype, @Cast("const int64_t*") long[] shape, + @Cast("uint64_t") long dim_count); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddInput( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name, + @Cast("const TRITONSERVER_DataType") int datatype, @Cast("const int64_t*") LongPointer shape, + @Cast("uint64_t") long dim_count); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddInput( + TRITONSERVER_InferenceRequest inference_request, String name, + @Cast("const TRITONSERVER_DataType") int datatype, @Cast("const int64_t*") LongBuffer shape, + @Cast("uint64_t") long dim_count); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddInput( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name, + @Cast("const TRITONSERVER_DataType") int datatype, @Cast("const int64_t*") long[] shape, + @Cast("uint64_t") long dim_count); + +/** Remove an input from a request. + * + * @param inference_request The request object. + * @param name The name of the input. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveInput( + TRITONSERVER_InferenceRequest inference_request, String name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveInput( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name); + +/** Remove all inputs from a request. + * + * @param inference_request The request object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveAllInputs( + TRITONSERVER_InferenceRequest inference_request); + +/** Assign a buffer of data to an input. The buffer will be appended + * to any existing buffers for that input. The 'inference_request' + * object takes ownership of the buffer and so the caller should not + * modify or free the buffer until that ownership is released by + * 'inference_request' being deleted or by the input being removed + * from 'inference_request'. + * + * @param inference_request The request object. + * @param name The name of the input. + * @param base The base address of the input data. + * @param byte_size The size, in bytes, of the input data. + * @param memory_type The memory type of the input data. + * @param memory_type_id The memory type id of the input data. + * @return a TRITONSERVER_Error indicating success or failure. */ +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAppendInputData( + TRITONSERVER_InferenceRequest inference_request, String name, + @Const Pointer base, @Cast("size_t") long byte_size, @Cast("TRITONSERVER_MemoryType") int memory_type, + @Cast("int64_t") long memory_type_id); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAppendInputData( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name, + @Const Pointer base, @Cast("size_t") long byte_size, @Cast("TRITONSERVER_MemoryType") int memory_type, + @Cast("int64_t") long memory_type_id); + +/** Assign a buffer of data to an input for execution on all model instances + * with the specified host policy. The buffer will be appended to any existing + * buffers for that input on all devices with this host policy. The + * 'inference_request' object takes ownership of the buffer and so the caller + * should not modify or free the buffer until that ownership is released by + * 'inference_request' being deleted or by the input being removed from + * 'inference_request'. If the execution is scheduled on a device that does not + * have a input buffer specified using this function, then the input buffer + * specified with TRITONSERVER_InferenceRequestAppendInputData will be used so + * a non-host policy specific version of data must be added using that API. + * @param inference_request The request object. + * @param name The name of the input. + * @param base The base address of the input data. + * @param byte_size The size, in bytes, of the input data. + * @param memory_type The memory type of the input data. + * @param memory_type_id The memory type id of the input data. + * @param host_policy_name All model instances executing with this host_policy + * will use this input buffer for execution. + * @return a TRITONSERVER_Error indicating success or failure. */ +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAppendInputDataWithHostPolicy( + TRITONSERVER_InferenceRequest inference_request, String name, + @Const Pointer base, @Cast("size_t") long byte_size, @Cast("TRITONSERVER_MemoryType") int memory_type, + @Cast("int64_t") long memory_type_id, String host_policy_name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAppendInputDataWithHostPolicy( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name, + @Const Pointer base, @Cast("size_t") long byte_size, @Cast("TRITONSERVER_MemoryType") int memory_type, + @Cast("int64_t") long memory_type_id, @Cast("const char*") BytePointer host_policy_name); + +/** Clear all input data from an input, releasing ownership of the + * buffer(s) that were appended to the input with + * TRITONSERVER_InferenceRequestAppendInputData or + * TRITONSERVER_InferenceRequestAppendInputDataWithHostPolicy + * @param inference_request The request object. + * @param name The name of the input. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveAllInputData( + TRITONSERVER_InferenceRequest inference_request, String name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveAllInputData( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name); + +/** Add an output request to an inference request. + * + * @param inference_request The request object. + * @param name The name of the output. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddRequestedOutput( + TRITONSERVER_InferenceRequest inference_request, String name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestAddRequestedOutput( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name); + +/** Remove an output request from an inference request. + * + * @param inference_request The request object. + * @param name The name of the output. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveRequestedOutput( + TRITONSERVER_InferenceRequest inference_request, String name); +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveRequestedOutput( + TRITONSERVER_InferenceRequest inference_request, @Cast("const char*") BytePointer name); + +/** Remove all output requests from an inference request. + * + * @param inference_request The request object. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestRemoveAllRequestedOutputs( + TRITONSERVER_InferenceRequest inference_request); + +/** Set the release callback for an inference request. The release + * callback is called by Triton to return ownership of the request + * object. + * + * @param inference_request The request object. + * @param request_release_fn The function called to return ownership + * of the 'inference_request' object. + * @param request_release_userp User-provided pointer that is + * delivered to the 'request_release_fn' callback. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetReleaseCallback( + TRITONSERVER_InferenceRequest inference_request, + TRITONSERVER_InferenceRequestReleaseFn_t request_release_fn, + Pointer request_release_userp); + +/** Set the allocator and response callback for an inference + * request. The allocator is used to allocate buffers for any output + * tensors included in responses that are produced for this + * request. The response callback is called to return response + * objects representing responses produced for this request. + * + * @param inference_request The request object. + * @param response_allocator The TRITONSERVER_ResponseAllocator to use + * to allocate buffers to hold inference results. + * @param response_allocator_userp User-provided pointer that is + * delivered to the response allocator's start and allocation functions. + * @param response_fn The function called to deliver an inference + * response for this request. + * @param response_userp User-provided pointer that is delivered to + * the 'response_fn' callback. + * @return a TRITONSERVER_Error indicating success or failure. */ + +/// +/// +/// +public static native TRITONSERVER_Error TRITONSERVER_InferenceRequestSetResponseCallback( + TRITONSERVER_InferenceRequest inference_request, + TRITONSERVER_ResponseAllocator response_allocator, + Pointer response_allocator_userp, + TRITONSERVER_InferenceResponseCompleteFn_t response_fn, + Pointer response_userp); + +/** TRITONSERVER_InferenceResponse + * + * Object representing an inference response. The inference response + * provides the meta-data and output tensor values calculated by the + * inference. + * +
+ * Delete an inference response object.
+ *
+ * @param inference_response The response object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseDelete(
+ TRITONSERVER_InferenceResponse inference_response);
+
+/** Return the error status of an inference response. Return a
+ * TRITONSERVER_Error object on failure, return nullptr on success.
+ * The returned error object is owned by 'inference_response' and so
+ * should not be deleted by the caller.
+ *
+ * @param inference_response The response object.
+ * @return a TRITONSERVER_Error indicating the success or failure
+ * status of the response. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseError(
+ TRITONSERVER_InferenceResponse inference_response);
+
+/** Get model used to produce a response. The caller does not own the
+ * returned model name value and must not modify or delete it. The
+ * lifetime of all returned values extends until 'inference_response'
+ * is deleted.
+ *
+ * @param inference_response The response object.
+ * @param model_name Returns the name of the model.
+ * @param model_version Returns the version of the model.
+ * this response.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseModel(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("const char**") PointerPointer model_name,
+ @Cast("int64_t*") LongPointer model_version);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseModel(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("const char**") @ByPtrPtr BytePointer model_name,
+ @Cast("int64_t*") LongPointer model_version);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseModel(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("const char**") @ByPtrPtr ByteBuffer model_name,
+ @Cast("int64_t*") LongBuffer model_version);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseModel(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("const char**") @ByPtrPtr byte[] model_name,
+ @Cast("int64_t*") long[] model_version);
+
+/** Get the ID of the request corresponding to a response. The caller
+ * does not own the returned ID and must not modify or delete it. The
+ * lifetime of all returned values extends until 'inference_response'
+ * is deleted.
+ *
+ * @param inference_response The response object.
+ * @param request_id Returns the ID of the request corresponding to
+ * this response.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseId(
+ TRITONSERVER_InferenceResponse inference_response,
+ @Cast("const char**") PointerPointer request_id);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseId(
+ TRITONSERVER_InferenceResponse inference_response,
+ @Cast("const char**") @ByPtrPtr BytePointer request_id);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseId(
+ TRITONSERVER_InferenceResponse inference_response,
+ @Cast("const char**") @ByPtrPtr ByteBuffer request_id);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseId(
+ TRITONSERVER_InferenceResponse inference_response,
+ @Cast("const char**") @ByPtrPtr byte[] request_id);
+
+/** Get the number of parameters available in the response.
+ *
+ * @param inference_response The response object.
+ * @param count Returns the number of parameters.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseParameterCount(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("uint32_t*") IntPointer count);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseParameterCount(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("uint32_t*") IntBuffer count);
+public static native TRITONSERVER_Error TRITONSERVER_InferenceResponseParameterCount(
+ TRITONSERVER_InferenceResponse inference_response, @Cast("uint32_t*") int[] count);
+
+/** Get all information about a parameter. The caller does not own any
+ * of the returned values and must not modify or delete them. The
+ * lifetime of all returned values extends until 'inference_response'
+ * is deleted.
+ *
+ * The 'vvalue' returns a void* pointer that must be cast
+ * appropriately based on 'type'. For example:
+ *
+ * void* vvalue;
+ * TRITONSERVER_ParameterType type;
+ * TRITONSERVER_InferenceResponseParameter(
+ * response, index, &name, &type, &vvalue);
+ * switch (type) {
+ * case TRITONSERVER_PARAMETER_BOOL:
+ * bool value = *(reinterpret_cast
+ * Model control modes */
+/** enum TRITONSERVER_ModelControlMode */
+public static final int
+ TRITONSERVER_MODEL_CONTROL_NONE = 0,
+ TRITONSERVER_MODEL_CONTROL_POLL = 1,
+ TRITONSERVER_MODEL_CONTROL_EXPLICIT = 2;
+
+/** Rate limit modes */
+/** enum TRITONSERVER_RateLimitMode */
+public static final int
+ TRITONSERVER_RATE_LIMIT_OFF = 0,
+ TRITONSERVER_RATE_LIMIT_EXEC_COUNT = 1;
+
+/** Create a new server options object. The caller takes ownership of
+ * the TRITONSERVER_ServerOptions object and must call
+ * TRITONSERVER_ServerOptionsDelete to release the object.
+ *
+ * @param options Returns the new server options object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsNew(
+ @Cast("TRITONSERVER_ServerOptions**") PointerPointer options);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsNew(
+ @ByPtrPtr TRITONSERVER_ServerOptions options);
+
+/** Delete a server options object.
+ *
+ * @param options The server options object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsDelete(
+ TRITONSERVER_ServerOptions options);
+
+/** Set the textual ID for the server in a server options. The ID is a
+ * name that identifies the server.
+ *
+ * @param options The server options object.
+ * @param server_id The server identifier.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetServerId(
+ TRITONSERVER_ServerOptions options, String server_id);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetServerId(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer server_id);
+
+/** Set the model repository path in a server options. The path must be
+ * the full absolute path to the model repository. This function can be called
+ * multiple times with different paths to set multiple model repositories.
+ * Note that if a model is not unique across all model repositories
+ * at any time, the model will not be available.
+ *
+ * @param options The server options object.
+ * @param model_repository_path The full path to the model repository.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetModelRepositoryPath(
+ TRITONSERVER_ServerOptions options, String model_repository_path);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetModelRepositoryPath(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer model_repository_path);
+
+/** Set the model control mode in a server options. For each mode the models
+ * will be managed as the following:
+ *
+ * TRITONSERVER_MODEL_CONTROL_NONE: the models in model repository will be
+ * loaded on startup. After startup any changes to the model repository will
+ * be ignored. Calling TRITONSERVER_ServerPollModelRepository will result in
+ * an error.
+ *
+ * TRITONSERVER_MODEL_CONTROL_POLL: the models in model repository will be
+ * loaded on startup. The model repository can be polled periodically using
+ * TRITONSERVER_ServerPollModelRepository and the server will load, unload,
+ * and updated models according to changes in the model repository.
+ *
+ * TRITONSERVER_MODEL_CONTROL_EXPLICIT: the models in model repository will
+ * not be loaded on startup. The corresponding model control APIs must be
+ * called to load / unload a model in the model repository.
+ *
+ * @param options The server options object.
+ * @param mode The mode to use for the model control.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetModelControlMode(
+ TRITONSERVER_ServerOptions options, @Cast("TRITONSERVER_ModelControlMode") int mode);
+
+/** Set the model to be loaded at startup in a server options. The model must be
+ * present in one, and only one, of the specified model repositories.
+ * This function can be called multiple times with different model name
+ * to set multiple startup models.
+ * Note that it only takes affect on TRITONSERVER_MODEL_CONTROL_EXPLICIT mode.
+ *
+ * @param options The server options object.
+ * @param mode_name The name of the model to load on startup.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetStartupModel(
+ TRITONSERVER_ServerOptions options, String model_name);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetStartupModel(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer model_name);
+
+/** Enable or disable strict model configuration handling in a server
+ * options.
+ *
+ * @param options The server options object.
+ * @param strict True to enable strict model configuration handling,
+ * false to disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetStrictModelConfig(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean strict);
+
+/** Set the rate limit mode in a server options.
+ *
+ * TRITONSERVER_RATE_LIMIT_EXEC_COUNT: The rate limiting prioritizes the
+ * inference execution using the number of times each instance has got a
+ * chance to run. The execution gets to run only when its resource
+ * constraints are satisfied.
+ *
+ * TRITONSERVER_RATE_LIMIT_OFF: The rate limiting is turned off and the
+ * inference gets executed whenever an instance is available.
+ *
+ * @param options The server options object.
+ * @param mode The mode to use for the rate limiting. By default, execution
+ * count is used to determine the priorities.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetRateLimiterMode(
+ TRITONSERVER_ServerOptions options, @Cast("TRITONSERVER_RateLimitMode") int mode);
+
+/** Add resource count for rate limiting.
+ *
+ * @param options The server options object.
+ * @param name The name of the resource.
+ * @param count The count of the resource.
+ * @param device The device identifier for the resource. A value of -1
+ * indicates that the specified number of resources are available on every
+ * device. The device value is ignored for a global resource. The server
+ * will use the rate limiter configuration specified for instance groups
+ * in model config to determine whether resource is global. In case of
+ * conflicting resource type in different model configurations, server
+ * will raise an appropriate error while loading model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsAddRateLimiterResource(
+ TRITONSERVER_ServerOptions options, String resource_name,
+ @Cast("const size_t") long resource_count, int device);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsAddRateLimiterResource(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer resource_name,
+ @Cast("const size_t") long resource_count, int device);
+
+/** Set the total pinned memory byte size that the server can allocate
+ * in a server options. The pinned memory pool will be shared across
+ * Triton itself and the backends that use
+ * TRITONBACKEND_MemoryManager to allocate memory.
+ *
+ * @param options The server options object.
+ * @param size The pinned memory pool byte size.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetPinnedMemoryPoolByteSize(
+ TRITONSERVER_ServerOptions options, @Cast("uint64_t") long size);
+
+/** Set the total CUDA memory byte size that the server can allocate
+ * on given GPU device in a server options. The pinned memory pool
+ * will be shared across Triton itself and the backends that use
+ * TRITONBACKEND_MemoryManager to allocate memory.
+ *
+ * @param options The server options object.
+ * @param gpu_device The GPU device to allocate the memory pool.
+ * @param size The CUDA memory pool byte size.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetCudaMemoryPoolByteSize(
+ TRITONSERVER_ServerOptions options, int gpu_device, @Cast("uint64_t") long size);
+
+/** Set the minimum support CUDA compute capability in a server
+ * options.
+ *
+ * @param options The server options object.
+ * @param cc The minimum CUDA compute capability.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetMinSupportedComputeCapability(
+ TRITONSERVER_ServerOptions options, double cc);
+
+/** Enable or disable exit-on-error in a server options.
+ *
+ * @param options The server options object.
+ * @param exit True to enable exiting on intialization error, false
+ * to continue.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetExitOnError(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean exit);
+
+/** Enable or disable strict readiness handling in a server options.
+ *
+ * @param options The server options object.
+ * @param strict True to enable strict readiness handling, false to
+ * disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetStrictReadiness(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean strict);
+
+/** Set the exit timeout, in seconds, for the server in a server
+ * options.
+ *
+ * @param options The server options object.
+ * @param timeout The exit timeout, in seconds.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetExitTimeout(
+ TRITONSERVER_ServerOptions options, @Cast("unsigned int") int timeout);
+
+/** Set the number of threads used in buffer manager in a server options.
+ *
+ * @param thread_count The number of threads.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetBufferManagerThreadCount(
+ TRITONSERVER_ServerOptions options, @Cast("unsigned int") int thread_count);
+
+/** Enable or disable info level logging.
+ *
+ * @param options The server options object.
+ * @param log True to enable info logging, false to disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetLogInfo(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean log);
+
+/** Enable or disable warning level logging.
+ *
+ * @param options The server options object.
+ * @param log True to enable warning logging, false to disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetLogWarn(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean log);
+
+/** Enable or disable error level logging.
+ *
+ * @param options The server options object.
+ * @param log True to enable error logging, false to disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetLogError(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean log);
+
+/** Set verbose logging level. Level zero disables verbose logging.
+ *
+ * @param options The server options object.
+ * @param level The verbose logging level.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetLogVerbose(
+ TRITONSERVER_ServerOptions options, int level);
+
+/** Enable or disable metrics collection in a server options.
+ *
+ * @param options The server options object.
+ * @param metrics True to enable metrics, false to disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetMetrics(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean metrics);
+
+/** Enable or disable GPU metrics collection in a server options. GPU
+ * metrics are collected if both this option and
+ * TRITONSERVER_ServerOptionsSetMetrics are true.
+ *
+ * @param options The server options object.
+ * @param gpu_metrics True to enable GPU metrics, false to disable.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetGpuMetrics(
+ TRITONSERVER_ServerOptions options, @Cast("bool") boolean gpu_metrics);
+
+/** Set the directory containing backend shared libraries. This
+ * directory is searched last after the version and model directory
+ * in the model repository when looking for the backend shared
+ * library for a model. If the backend is named 'be' the directory
+ * searched is 'backend_dir'/be/libtriton_be.so.
+ *
+ * @param options The server options object.
+ * @param backend_dir The full path of the backend directory.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetBackendDirectory(
+ TRITONSERVER_ServerOptions options, String backend_dir);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetBackendDirectory(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer backend_dir);
+
+/** Set the directory containing repository agent shared libraries. This
+ * directory is searched when looking for the repository agent shared
+ * library for a model. If the backend is named 'ra' the directory
+ * searched is 'repoagent_dir'/ra/libtritonrepoagent_ra.so.
+ *
+ * @param options The server options object.
+ * @param repoagent_dir The full path of the repository agent directory.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetRepoAgentDirectory(
+ TRITONSERVER_ServerOptions options, String repoagent_dir);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetRepoAgentDirectory(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer repoagent_dir);
+
+/** Set a configuration setting for a named backend in a server
+ * options.
+ *
+ * @param options The server options object.
+ * @param backend_name The name of the backend.
+ * @param setting The name of the setting.
+ * @param value The setting value.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetBackendConfig(
+ TRITONSERVER_ServerOptions options, String backend_name,
+ String setting, String value);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetBackendConfig(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer backend_name,
+ @Cast("const char*") BytePointer setting, @Cast("const char*") BytePointer value);
+
+/** Set a host policy setting for a given policy name in a server options.
+ *
+ * @param options The server options object.
+ * @param policy_name The name of the policy.
+ * @param setting The name of the setting.
+ * @param value The setting value.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetHostPolicy(
+ TRITONSERVER_ServerOptions options, String policy_name,
+ String setting, String value);
+public static native TRITONSERVER_Error TRITONSERVER_ServerOptionsSetHostPolicy(
+ TRITONSERVER_ServerOptions options, @Cast("const char*") BytePointer policy_name,
+ @Cast("const char*") BytePointer setting, @Cast("const char*") BytePointer value);
+
+/** TRITONSERVER_Server
+ *
+ * An inference server.
+ *
+
+ * Model batch flags. The enum values must be power-of-2 values. */
+/** enum TRITONSERVER_ModelBatchFlag */
+public static final int
+ TRITONSERVER_BATCH_UNKNOWN = 1,
+ TRITONSERVER_BATCH_FIRST_DIM = 2;
+
+/** Model index flags. The enum values must be power-of-2 values. */
+/** enum TRITONSERVER_ModelIndexFlag */
+public static final int
+ TRITONSERVER_INDEX_FLAG_READY = 1;
+
+/** Model transaction policy flags. The enum values must be
+ * power-of-2 values. */
+/** enum TRITONSERVER_ModelTxnPropertyFlag */
+public static final int
+ TRITONSERVER_TXN_ONE_TO_ONE = 1,
+ TRITONSERVER_TXN_DECOUPLED = 2;
+
+/** Create a new server object. The caller takes ownership of the
+ * TRITONSERVER_Server object and must call TRITONSERVER_ServerDelete
+ * to release the object.
+ *
+ * @param server Returns the new inference server object.
+ * @param options The inference server options object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerNew(
+ @Cast("TRITONSERVER_Server**") PointerPointer server, TRITONSERVER_ServerOptions options);
+public static native TRITONSERVER_Error TRITONSERVER_ServerNew(
+ @ByPtrPtr TRITONSERVER_Server server, TRITONSERVER_ServerOptions options);
+
+/** Delete a server object. If server is not already stopped it is
+ * stopped before being deleted.
+ *
+ * @param server The inference server object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerDelete(
+ TRITONSERVER_Server server);
+
+/** Stop a server object. A server can't be restarted once it is
+ * stopped.
+ *
+ * @param server The inference server object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerStop(
+ TRITONSERVER_Server server);
+
+/** Check the model repository for changes and update server state
+ * based on those changes.
+ *
+ * @param server The inference server object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerPollModelRepository(TRITONSERVER_Server server);
+
+/** Is the server live?
+ *
+ * @param server The inference server object.
+ * @param live Returns true if server is live, false otherwise.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerIsLive(
+ TRITONSERVER_Server server, @Cast("bool*") boolean[] live);
+public static native TRITONSERVER_Error TRITONSERVER_ServerIsLive(
+ TRITONSERVER_Server server, @Cast("bool*") BoolPointer live);
+
+/** Is the server ready?
+ *
+ * @param server The inference server object.
+ * @param ready Returns true if server is ready, false otherwise.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerIsReady(
+ TRITONSERVER_Server server, @Cast("bool*") boolean[] ready);
+public static native TRITONSERVER_Error TRITONSERVER_ServerIsReady(
+ TRITONSERVER_Server server, @Cast("bool*") BoolPointer ready);
+
+/** Is the model ready?
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model to get readiness for.
+ * @param model_version The version of the model to get readiness
+ * for. If -1 then the server will choose a version based on the
+ * model's policy.
+ * @param ready Returns true if server is ready, false otherwise.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelIsReady(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("bool*") boolean[] ready);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelIsReady(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("bool*") BoolPointer ready);
+
+/** Get the batch properties of the model. The properties are
+ * communicated by a flags value and an (optional) object returned by
+ * 'voidp'.
+ *
+ * - TRITONSERVER_BATCH_UNKNOWN: Triton cannot determine the
+ * batching properties of the model. This means that the model
+ * does not support batching in any way that is useable by
+ * Triton. The returned 'voidp' value is nullptr.
+ *
+ * - TRITONSERVER_BATCH_FIRST_DIM: The model supports batching
+ * along the first dimension of every input and output
+ * tensor. Triton schedulers that perform batching can
+ * automatically batch inference requests along this dimension.
+ * The returned 'voidp' value is nullptr.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @param model_version The version of the model. If -1 then the
+ * server will choose a version based on the model's policy.
+ * @param flags Returns flags indicating the batch properties of the
+ * model.
+ * @param voidp If non-nullptr, returns a point specific to the
+ * 'flags' value.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntPointer flags, @Cast("void**") PointerPointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntPointer flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntBuffer flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") int[] flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntPointer flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntBuffer flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelBatchProperties(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") int[] flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+
+/** Get the transaction policy of the model. The policy is
+ * communicated by a flags value.
+ *
+ * - TRITONSERVER_TXN_ONE_TO_ONE: The model generates exactly
+ * one response per request.
+ *
+ * - TRITONSERVER_TXN_DECOUPLED: The model may generate zero
+ * to many responses per request.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @param model_version The version of the model. If -1 then the
+ * server will choose a version based on the model's policy.
+ * @param txn_flags Returns flags indicating the transaction policy of the
+ * model.
+ * @param voidp If non-nullptr, returns a point specific to the 'flags' value.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntPointer txn_flags, @Cast("void**") PointerPointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntPointer txn_flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntBuffer txn_flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") int[] txn_flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntPointer txn_flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") IntBuffer txn_flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelTransactionProperties(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("uint32_t*") int[] txn_flags, @Cast("void**") @ByPtrPtr Pointer voidp);
+
+/** Get the metadata of the server as a TRITONSERVER_Message object.
+ * The caller takes ownership of the message object and must call
+ * TRITONSERVER_MessageDelete to release the object.
+ *
+ * @param server The inference server object.
+ * @param server_metadata Returns the server metadata message.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerMetadata(
+ TRITONSERVER_Server server, @Cast("TRITONSERVER_Message**") PointerPointer server_metadata);
+public static native TRITONSERVER_Error TRITONSERVER_ServerMetadata(
+ TRITONSERVER_Server server, @ByPtrPtr TRITONSERVER_Message server_metadata);
+
+/** Get the metadata of a model as a TRITONSERVER_Message
+ * object. The caller takes ownership of the message object and must
+ * call TRITONSERVER_MessageDelete to release the object.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @param model_version The version of the model.
+ * If -1 then the server will choose a version based on the model's
+ * policy.
+ * @param model_metadata Returns the model metadata message.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelMetadata(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("TRITONSERVER_Message**") PointerPointer model_metadata);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelMetadata(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @ByPtrPtr TRITONSERVER_Message model_metadata);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelMetadata(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @ByPtrPtr TRITONSERVER_Message model_metadata);
+
+/** Get the statistics of a model as a TRITONSERVER_Message
+ * object. The caller takes ownership of the object and must call
+ * TRITONSERVER_MessageDelete to release the object.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * If empty, then statistics for all available models will be returned,
+ * and the server will choose a version based on those models' policies.
+ * @param model_version The version of the model. If -1 then the
+ * server will choose a version based on the model's policy.
+ * @param model_stats Returns the model statistics message.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelStatistics(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("TRITONSERVER_Message**") PointerPointer model_stats);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelStatistics(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @ByPtrPtr TRITONSERVER_Message model_stats);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelStatistics(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @ByPtrPtr TRITONSERVER_Message model_stats);
+
+/** Get the configuration of a model as a TRITONSERVER_Message object.
+ * The caller takes ownership of the message object and must call
+ * TRITONSERVER_MessageDelete to release the object.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @param model_version The version of the model. If -1 then the
+ * server will choose a version based on the model's policy.
+ * @param config_version The model configuration will be returned in
+ * a format matching this version. If the configuration cannot be
+ * represented in the requested version's format then an error will
+ * be returned. Currently only version 1 is supported.
+ * @param model_config Returns the model config message.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelConfig(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("const uint32_t") int config_version,
+ @Cast("TRITONSERVER_Message**") PointerPointer model_config);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelConfig(
+ TRITONSERVER_Server server, String model_name,
+ @Cast("const int64_t") long model_version, @Cast("const uint32_t") int config_version,
+ @ByPtrPtr TRITONSERVER_Message model_config);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelConfig(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name,
+ @Cast("const int64_t") long model_version, @Cast("const uint32_t") int config_version,
+ @ByPtrPtr TRITONSERVER_Message model_config);
+
+/** Get the index of all unique models in the model repositories as a
+ * TRITONSERVER_Message object. The caller takes ownership of the
+ * message object and must call TRITONSERVER_MessageDelete to release
+ * the object.
+ *
+ * If TRITONSERVER_INDEX_FLAG_READY is set in 'flags' only the models
+ * that are loaded into the server and ready for inferencing are
+ * returned.
+ *
+ * @param server The inference server object.
+ * @param flags TRITONSERVER_ModelIndexFlag flags that control how to
+ * collect the index.
+ * @param model_index Return the model index message that holds the
+ * index of all models contained in the server's model repository(s).
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelIndex(
+ TRITONSERVER_Server server, @Cast("uint32_t") int flags,
+ @Cast("TRITONSERVER_Message**") PointerPointer model_index);
+public static native TRITONSERVER_Error TRITONSERVER_ServerModelIndex(
+ TRITONSERVER_Server server, @Cast("uint32_t") int flags,
+ @ByPtrPtr TRITONSERVER_Message model_index);
+
+/** Load the requested model or reload the model if it is already
+ * loaded. The function does not return until the model is loaded or
+ * fails to load. Returned error indicates if model loaded
+ * successfully or not.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerLoadModel(
+ TRITONSERVER_Server server, String model_name);
+public static native TRITONSERVER_Error TRITONSERVER_ServerLoadModel(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name);
+
+/** Unload the requested model. Unloading a model that is not loaded
+ * on server has no affect and success code will be returned.
+ * The function does not wait for the requested model to be fully unload
+ * and success code will be returned.
+ * Returned error indicates if model unloaded successfully or not.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerUnloadModel(
+ TRITONSERVER_Server server, String model_name);
+public static native TRITONSERVER_Error TRITONSERVER_ServerUnloadModel(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name);
+
+/** Unload the requested model, and also unload any dependent model that
+ * was loaded along with the requested model (for example, the models composing
+ * an ensemble). Unloading a model that is not loaded
+ * on server has no affect and success code will be returned.
+ * The function does not wait for the requested model and all dependent
+ * models to be fully unload and success code will be returned.
+ * Returned error indicates if model unloaded successfully or not.
+ *
+ * @param server The inference server object.
+ * @param model_name The name of the model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerUnloadModelAndDependents(
+ TRITONSERVER_Server server, String model_name);
+public static native TRITONSERVER_Error TRITONSERVER_ServerUnloadModelAndDependents(
+ TRITONSERVER_Server server, @Cast("const char*") BytePointer model_name);
+
+/** Get the current metrics for the server. The caller takes ownership
+ * of the metrics object and must call TRITONSERVER_MetricsDelete to
+ * release the object.
+ *
+ * @param server The inference server object.
+ * @param metrics Returns the metrics.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONSERVER_ServerMetrics(
+ TRITONSERVER_Server server, @Cast("TRITONSERVER_Metrics**") PointerPointer metrics);
+public static native TRITONSERVER_Error TRITONSERVER_ServerMetrics(
+ TRITONSERVER_Server server, @ByPtrPtr TRITONSERVER_Metrics metrics);
+
+/** Perform inference using the meta-data and inputs supplied by the
+ * 'inference_request'. If the function returns success, then the
+ * caller releases ownership of 'inference_request' and must not
+ * access it in any way after this call, until ownership is returned
+ * via the 'request_release_fn' callback registered in the request
+ * object with TRITONSERVER_InferenceRequestSetReleaseCallback.
+ *
+ * The function unconditionally takes ownership of 'trace' and so the
+ * caller must not access it in any way after this call (except in
+ * the trace id callback) until ownership is returned via the trace's
+ * release_fn callback.
+ *
+ * Responses produced for this request are returned using the
+ * allocator and callback registered with the request by
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ *
+ * @param server The inference server object.
+ * @param inference_request The request object.
+ * @param trace The trace object for this request, or nullptr if no
+ * tracing.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+public static native TRITONSERVER_Error TRITONSERVER_ServerInferAsync(
+ TRITONSERVER_Server server,
+ TRITONSERVER_InferenceRequest inference_request,
+ TRITONSERVER_InferenceTrace trace);
+
+
+// #ifdef __cplusplus
+// #endif
+
+
+// Parsed from tritonbackend.h
+
+// Copyright 2020-2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions
+// are met:
+// * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+// * Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the distribution.
+// * Neither the name of NVIDIA CORPORATION nor the names of its
+// contributors may be used to endorse or promote products derived
+// from this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+// #pragma once
+
+// #include
+ * Allocate a contiguous block of memory of a specific type using a
+ * memory manager. Two error codes have specific interpretations for
+ * this function:
+ *
+ * TRITONSERVER_ERROR_UNSUPPORTED: Indicates that Triton is
+ * incapable of allocating the requested memory type and memory
+ * type ID. Requests for the memory type and ID will always fail
+ * no matter 'byte_size' of the request.
+ *
+ * TRITONSERVER_ERROR_UNAVAILABLE: Indicates that Triton can
+ * allocate the memory type and ID but that currently it cannot
+ * allocate a contiguous block of memory of the requested
+ * 'byte_size'.
+ *
+ * @param manager The memory manager.
+ * @param buffer Returns the allocated memory.
+ * @param memory_type The type of memory to allocate.
+ * @param memory_type_id The ID associated with the memory type to
+ * allocate. For GPU memory this indicates the device ID of the GPU
+ * to allocate from.
+ * @param byte_size The size of memory to allocate, in bytes.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_MemoryManagerAllocate(
+ TRITONBACKEND_MemoryManager manager, @Cast("void**") PointerPointer buffer,
+ @Cast("const TRITONSERVER_MemoryType") int memory_type, @Cast("const int64_t") long memory_type_id,
+ @Cast("const uint64_t") long byte_size);
+public static native TRITONSERVER_Error TRITONBACKEND_MemoryManagerAllocate(
+ TRITONBACKEND_MemoryManager manager, @Cast("void**") @ByPtrPtr Pointer buffer,
+ @Cast("const TRITONSERVER_MemoryType") int memory_type, @Cast("const int64_t") long memory_type_id,
+ @Cast("const uint64_t") long byte_size);
+
+/** Free a buffer that was previously allocated with
+ * TRITONBACKEND_MemoryManagerAllocate. The call must provide the
+ * same values for 'memory_type' and 'memory_type_id' as were used
+ * when the buffer was allocate or else the behavior is undefined.
+ *
+ * @param manager The memory manager.
+ * @param buffer The allocated memory buffer to free.
+ * @param memory_type The type of memory of the buffer.
+ * @param memory_type_id The ID associated with the memory type of
+ * the buffer.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_MemoryManagerFree(
+ TRITONBACKEND_MemoryManager manager, Pointer buffer,
+ @Cast("const TRITONSERVER_MemoryType") int memory_type, @Cast("const int64_t") long memory_type_id);
+
+/**
+ * TRITONBACKEND_Input
+ *
+ * Object representing an input tensor.
+ *
+
+ * Get the name and properties of an input tensor. The returned
+ * strings and other properties are owned by the input, not the
+ * caller, and so should not be modified or freed.
+ *
+ * @param input The input tensor.
+ * @param name If non-nullptr, returns the tensor name.
+ * @param datatype If non-nullptr, returns the tensor datatype.
+ * @param shape If non-nullptr, returns the tensor shape.
+ * @param dim_count If non-nullptr, returns the number of dimensions
+ * in the tensor shape.
+ * @param byte_size If non-nullptr, returns the size of the available
+ * data for the tensor, in bytes. This size reflects the actual data
+ * available, and does not necessarily match what is
+ * expected/required for the tensor given its shape and datatype. It
+ * is the responsibility of the backend to handle mismatches in these
+ * sizes appropriately.
+ * @param buffer_count If non-nullptr, returns the number of buffers
+ * holding the contents of the tensor. These buffers are accessed
+ * using TRITONBACKEND_InputBuffer.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_InputProperties(
+ TRITONBACKEND_Input input, @Cast("const char**") PointerPointer name,
+ @Cast("TRITONSERVER_DataType*") IntPointer datatype, @Cast("const int64_t**") PointerPointer shape,
+ @Cast("uint32_t*") IntPointer dims_count, @Cast("uint64_t*") LongPointer byte_size, @Cast("uint32_t*") IntPointer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputProperties(
+ TRITONBACKEND_Input input, @Cast("const char**") @ByPtrPtr BytePointer name,
+ @Cast("TRITONSERVER_DataType*") IntPointer datatype, @Cast("const int64_t**") @ByPtrPtr LongPointer shape,
+ @Cast("uint32_t*") IntPointer dims_count, @Cast("uint64_t*") LongPointer byte_size, @Cast("uint32_t*") IntPointer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputProperties(
+ TRITONBACKEND_Input input, @Cast("const char**") @ByPtrPtr ByteBuffer name,
+ @Cast("TRITONSERVER_DataType*") IntBuffer datatype, @Cast("const int64_t**") @ByPtrPtr LongBuffer shape,
+ @Cast("uint32_t*") IntBuffer dims_count, @Cast("uint64_t*") LongBuffer byte_size, @Cast("uint32_t*") IntBuffer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputProperties(
+ TRITONBACKEND_Input input, @Cast("const char**") @ByPtrPtr byte[] name,
+ @Cast("TRITONSERVER_DataType*") int[] datatype, @Cast("const int64_t**") @ByPtrPtr long[] shape,
+ @Cast("uint32_t*") int[] dims_count, @Cast("uint64_t*") long[] byte_size, @Cast("uint32_t*") int[] buffer_count);
+
+/** Get the name and properties of an input tensor associated with a given
+ * host policy. If there are no input buffers for the specified host policy,
+ * the properties of the fallback input buffers are returned. The returned
+ * strings and other properties are owned by the input, not the caller, and so
+ * should not be modified or freed.
+ *
+ * @param input The input tensor.
+ * @param host_policy_name The host policy name. Fallback input properties
+ * will be return if nullptr is provided.
+ * @param name If non-nullptr, returns the tensor name.
+ * @param datatype If non-nullptr, returns the tensor datatype.
+ * @param shape If non-nullptr, returns the tensor shape.
+ * @param dim_count If non-nullptr, returns the number of dimensions
+ * in the tensor shape.
+ * @param byte_size If non-nullptr, returns the size of the available
+ * data for the tensor, in bytes. This size reflects the actual data
+ * available, and does not necessarily match what is
+ * expected/required for the tensor given its shape and datatype. It
+ * is the responsibility of the backend to handle mismatches in these
+ * sizes appropriately.
+ * @param buffer_count If non-nullptr, returns the number of buffers
+ * holding the contents of the tensor. These buffers are accessed
+ * using TRITONBACKEND_InputBufferForHostPolicy.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name, @Cast("const char**") PointerPointer name,
+ @Cast("TRITONSERVER_DataType*") IntPointer datatype, @Cast("const int64_t**") PointerPointer shape,
+ @Cast("uint32_t*") IntPointer dims_count, @Cast("uint64_t*") LongPointer byte_size, @Cast("uint32_t*") IntPointer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name, @Cast("const char**") @ByPtrPtr BytePointer name,
+ @Cast("TRITONSERVER_DataType*") IntPointer datatype, @Cast("const int64_t**") @ByPtrPtr LongPointer shape,
+ @Cast("uint32_t*") IntPointer dims_count, @Cast("uint64_t*") LongPointer byte_size, @Cast("uint32_t*") IntPointer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, @Cast("const char*") BytePointer host_policy_name, @Cast("const char**") @ByPtrPtr ByteBuffer name,
+ @Cast("TRITONSERVER_DataType*") IntBuffer datatype, @Cast("const int64_t**") @ByPtrPtr LongBuffer shape,
+ @Cast("uint32_t*") IntBuffer dims_count, @Cast("uint64_t*") LongBuffer byte_size, @Cast("uint32_t*") IntBuffer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name, @Cast("const char**") @ByPtrPtr byte[] name,
+ @Cast("TRITONSERVER_DataType*") int[] datatype, @Cast("const int64_t**") @ByPtrPtr long[] shape,
+ @Cast("uint32_t*") int[] dims_count, @Cast("uint64_t*") long[] byte_size, @Cast("uint32_t*") int[] buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, @Cast("const char*") BytePointer host_policy_name, @Cast("const char**") @ByPtrPtr BytePointer name,
+ @Cast("TRITONSERVER_DataType*") IntPointer datatype, @Cast("const int64_t**") @ByPtrPtr LongPointer shape,
+ @Cast("uint32_t*") IntPointer dims_count, @Cast("uint64_t*") LongPointer byte_size, @Cast("uint32_t*") IntPointer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name, @Cast("const char**") @ByPtrPtr ByteBuffer name,
+ @Cast("TRITONSERVER_DataType*") IntBuffer datatype, @Cast("const int64_t**") @ByPtrPtr LongBuffer shape,
+ @Cast("uint32_t*") IntBuffer dims_count, @Cast("uint64_t*") LongBuffer byte_size, @Cast("uint32_t*") IntBuffer buffer_count);
+public static native TRITONSERVER_Error TRITONBACKEND_InputPropertiesForHostPolicy(
+ TRITONBACKEND_Input input, @Cast("const char*") BytePointer host_policy_name, @Cast("const char**") @ByPtrPtr byte[] name,
+ @Cast("TRITONSERVER_DataType*") int[] datatype, @Cast("const int64_t**") @ByPtrPtr long[] shape,
+ @Cast("uint32_t*") int[] dims_count, @Cast("uint64_t*") long[] byte_size, @Cast("uint32_t*") int[] buffer_count);
+
+/** Get a buffer holding (part of) the tensor data for an input. For a
+ * given input the number of buffers composing the input are found
+ * from 'buffer_count' returned by TRITONBACKEND_InputProperties. The
+ * returned buffer is owned by the input and so should not be
+ * modified or freed by the caller. The lifetime of the buffer
+ * matches that of the input and so the buffer should not be accessed
+ * after the input tensor object is released.
+ *
+ * @param input The input tensor.
+ * @param index The index of the buffer. Must be 0 <= index <
+ * buffer_count, where buffer_count is the value returned by
+ * TRITONBACKEND_InputProperties.
+ * @param buffer Returns a pointer to a contiguous block of data for
+ * the named input.
+ * @param buffer_byte_size Returns the size, in bytes, of 'buffer'.
+ * @param memory_type Acts as both input and output. On input gives
+ * the buffer memory type preferred by the function caller. Returns
+ * the actual memory type of 'buffer'.
+ * @param memory_type_id Acts as both input and output. On input
+ * gives the buffer memory type id preferred by the function caller.
+ * Returns the actual memory type id of 'buffer'.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_InputBuffer(
+ TRITONBACKEND_Input input, @Cast("const uint32_t") int index, @Cast("const void**") PointerPointer buffer,
+ @Cast("uint64_t*") LongPointer buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type,
+ @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBuffer(
+ TRITONBACKEND_Input input, @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer,
+ @Cast("uint64_t*") LongPointer buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type,
+ @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBuffer(
+ TRITONBACKEND_Input input, @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer,
+ @Cast("uint64_t*") LongBuffer buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") IntBuffer memory_type,
+ @Cast("int64_t*") LongBuffer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBuffer(
+ TRITONBACKEND_Input input, @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer,
+ @Cast("uint64_t*") long[] buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") int[] memory_type,
+ @Cast("int64_t*") long[] memory_type_id);
+
+/** Get a buffer holding (part of) the tensor data for an input for a specific
+ * host policy. If there are no input buffers specified for this host policy,
+ * the fallback input buffer is returned.
+ * For a given input the number of buffers composing the input are found
+ * from 'buffer_count' returned by TRITONBACKEND_InputPropertiesForHostPolicy.
+ * The returned buffer is owned by the input and so should not be modified or
+ * freed by the caller. The lifetime of the buffer matches that of the input
+ * and so the buffer should not be accessed after the input tensor object is
+ * released.
+ *
+ * @param input The input tensor.
+ * @param host_policy_name The host policy name. Fallback input buffer
+ * will be return if nullptr is provided.
+ * @param index The index of the buffer. Must be 0 <= index <
+ * buffer_count, where buffer_count is the value returned by
+ * TRITONBACKEND_InputPropertiesForHostPolicy.
+ * @param buffer Returns a pointer to a contiguous block of data for
+ * the named input.
+ * @param buffer_byte_size Returns the size, in bytes, of 'buffer'.
+ * @param memory_type Acts as both input and output. On input gives
+ * the buffer memory type preferred by the function caller. Returns
+ * the actual memory type of 'buffer'.
+ * @param memory_type_id Acts as both input and output. On input
+ * gives the buffer memory type id preferred by the function caller.
+ * Returns the actual memory type id of 'buffer'.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") PointerPointer buffer, @Cast("uint64_t*") LongPointer buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type, @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer, @Cast("uint64_t*") LongPointer buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type, @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, @Cast("const char*") BytePointer host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer, @Cast("uint64_t*") LongBuffer buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") IntBuffer memory_type, @Cast("int64_t*") LongBuffer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer, @Cast("uint64_t*") long[] buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") int[] memory_type, @Cast("int64_t*") long[] memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, @Cast("const char*") BytePointer host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer, @Cast("uint64_t*") LongPointer buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type, @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, String host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer, @Cast("uint64_t*") LongBuffer buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") IntBuffer memory_type, @Cast("int64_t*") LongBuffer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_InputBufferForHostPolicy(
+ TRITONBACKEND_Input input, @Cast("const char*") BytePointer host_policy_name,
+ @Cast("const uint32_t") int index, @Cast("const void**") @ByPtrPtr Pointer buffer, @Cast("uint64_t*") long[] buffer_byte_size,
+ @Cast("TRITONSERVER_MemoryType*") int[] memory_type, @Cast("int64_t*") long[] memory_type_id);
+
+/**
+ * TRITONBACKEND_Output
+ *
+ * Object representing a response output tensor.
+ *
+
+ * Get a buffer to use to hold the tensor data for the output. The
+ * returned buffer is owned by the output and so should not be freed
+ * by the caller. The caller can and should fill the buffer with the
+ * output data for the tensor. The lifetime of the buffer matches
+ * that of the output and so the buffer should not be accessed after
+ * the output tensor object is released.
+ *
+ * @param buffer Returns a pointer to a buffer where the contents of
+ * the output tensor should be placed.
+ * @param buffer_byte_size The size, in bytes, of the buffer required
+ * by the caller.
+ * @param memory_type Acts as both input and output. On input gives
+ * the buffer memory type preferred by the caller. Returns the
+ * actual memory type of 'buffer'.
+ * @param memory_type_id Acts as both input and output. On input
+ * gives the buffer memory type id preferred by the caller. Returns
+ * the actual memory type id of 'buffer'.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_OutputBuffer(
+ TRITONBACKEND_Output output, @Cast("void**") PointerPointer buffer,
+ @Cast("const uint64_t") long buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type,
+ @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_OutputBuffer(
+ TRITONBACKEND_Output output, @Cast("void**") @ByPtrPtr Pointer buffer,
+ @Cast("const uint64_t") long buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") IntPointer memory_type,
+ @Cast("int64_t*") LongPointer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_OutputBuffer(
+ TRITONBACKEND_Output output, @Cast("void**") @ByPtrPtr Pointer buffer,
+ @Cast("const uint64_t") long buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") IntBuffer memory_type,
+ @Cast("int64_t*") LongBuffer memory_type_id);
+public static native TRITONSERVER_Error TRITONBACKEND_OutputBuffer(
+ TRITONBACKEND_Output output, @Cast("void**") @ByPtrPtr Pointer buffer,
+ @Cast("const uint64_t") long buffer_byte_size, @Cast("TRITONSERVER_MemoryType*") int[] memory_type,
+ @Cast("int64_t*") long[] memory_type_id);
+
+/**
+ * TRITONBACKEND_Request
+ *
+ * Object representing an inference request.
+ *
+
+ * Get the ID of the request. Can be nullptr if request doesn't have
+ * an ID. The returned string is owned by the request, not the
+ * caller, and so should not be modified or freed.
+ *
+ * @param request The inference request.
+ * @param id Returns the ID.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestId(
+ TRITONBACKEND_Request request, @Cast("const char**") PointerPointer id);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestId(
+ TRITONBACKEND_Request request, @Cast("const char**") @ByPtrPtr BytePointer id);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestId(
+ TRITONBACKEND_Request request, @Cast("const char**") @ByPtrPtr ByteBuffer id);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestId(
+ TRITONBACKEND_Request request, @Cast("const char**") @ByPtrPtr byte[] id);
+
+/** Get the correlation ID of the request. Zero indicates that the
+ * request does not have a correlation ID.
+ *
+ * @param request The inference request.
+ * @param id Returns the correlation ID.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestCorrelationId(
+ TRITONBACKEND_Request request, @Cast("uint64_t*") LongPointer id);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestCorrelationId(
+ TRITONBACKEND_Request request, @Cast("uint64_t*") LongBuffer id);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestCorrelationId(
+ TRITONBACKEND_Request request, @Cast("uint64_t*") long[] id);
+
+/** Get the number of input tensors specified in the request.
+ *
+ * @param request The inference request.
+ * @param count Returns the number of input tensors.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputCount(
+ TRITONBACKEND_Request request, @Cast("uint32_t*") IntPointer count);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputCount(
+ TRITONBACKEND_Request request, @Cast("uint32_t*") IntBuffer count);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputCount(
+ TRITONBACKEND_Request request, @Cast("uint32_t*") int[] count);
+
+/** Get the name of an input tensor. The caller does not own
+ * the returned string and must not modify or delete it. The lifetime
+ * of the returned string extends only as long as 'request'.
+ *
+ * @param request The inference request.
+ * @param index The index of the input tensor. Must be 0 <= index <
+ * count, where count is the value returned by
+ * TRITONBACKEND_RequestInputCount.
+ * @param input_name Returns the name of the input tensor
+ * corresponding to the index.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") PointerPointer input_name);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") @ByPtrPtr BytePointer input_name);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") @ByPtrPtr ByteBuffer input_name);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") @ByPtrPtr byte[] input_name);
+
+/** Get a named request input. The lifetime of the returned input
+ * object matches that of the request and so the input object should
+ * not be accessed after the request object is released.
+ *
+ * @param request The inference request.
+ * @param name The name of the input.
+ * @param input Returns the input corresponding to the name.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInput(
+ TRITONBACKEND_Request request, String name,
+ @Cast("TRITONBACKEND_Input**") PointerPointer input);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInput(
+ TRITONBACKEND_Request request, String name,
+ @ByPtrPtr TRITONBACKEND_Input input);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInput(
+ TRITONBACKEND_Request request, @Cast("const char*") BytePointer name,
+ @ByPtrPtr TRITONBACKEND_Input input);
+
+/** Get a request input by index. The order of inputs in a given
+ * request is not necessarily consistent with other requests, even if
+ * the requests are in the same batch. As a result, you can not
+ * assume that an index obtained from one request will point to the
+ * same input in a different request.
+ *
+ * The lifetime of the returned input object matches that of the
+ * request and so the input object should not be accessed after the
+ * request object is released.
+ *
+ * @param request The inference request.
+ * @param index The index of the input tensor. Must be 0 <= index <
+ * count, where count is the value returned by
+ * TRITONBACKEND_RequestInputCount.
+ * @param input Returns the input corresponding to the index.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputByIndex(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("TRITONBACKEND_Input**") PointerPointer input);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestInputByIndex(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @ByPtrPtr TRITONBACKEND_Input input);
+
+/** Get the number of output tensors requested to be returned in the
+ * request.
+ *
+ * @param request The inference request.
+ * @param count Returns the number of output tensors.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputCount(
+ TRITONBACKEND_Request request, @Cast("uint32_t*") IntPointer count);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputCount(
+ TRITONBACKEND_Request request, @Cast("uint32_t*") IntBuffer count);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputCount(
+ TRITONBACKEND_Request request, @Cast("uint32_t*") int[] count);
+
+/** Get the name of a requested output tensor. The caller does not own
+ * the returned string and must not modify or delete it. The lifetime
+ * of the returned string extends only as long as 'request'.
+ *
+ * @param request The inference request.
+ * @param index The index of the requested output tensor. Must be 0
+ * <= index < count, where count is the value returned by
+ * TRITONBACKEND_RequestOutputCount.
+ * @param output_name Returns the name of the requested output tensor
+ * corresponding to the index.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") PointerPointer output_name);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") @ByPtrPtr BytePointer output_name);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") @ByPtrPtr ByteBuffer output_name);
+public static native TRITONSERVER_Error TRITONBACKEND_RequestOutputName(
+ TRITONBACKEND_Request request, @Cast("const uint32_t") int index,
+ @Cast("const char**") @ByPtrPtr byte[] output_name);
+
+/** Release the request. The request should be released when it is no
+ * longer needed by the backend. If this call returns with an error
+ * (i.e. non-nullptr) then the request was not released and ownership
+ * remains with the backend. If this call returns with success, the
+ * 'request' object is no longer owned by the backend and must not be
+ * used. Any tensor names, data types, shapes, input tensors,
+ * etc. returned by TRITONBACKEND_Request* functions for this request
+ * are no longer valid. If a persistent copy of that data is required
+ * it must be created before calling this function.
+ *
+ * @param request The inference request.
+ * @param release_flags Flags indicating what type of request release
+ * should be performed. @see TRITONSERVER_RequestReleaseFlag. @see
+ * TRITONSERVER_InferenceRequestReleaseFn_t.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_RequestRelease(
+ TRITONBACKEND_Request request, @Cast("uint32_t") int release_flags);
+
+/**
+ * TRITONBACKEND_ResponseFactory
+ *
+ * Object representing an inference response factory. Using a
+ * response factory is not required; instead a response can be
+ * generated directly from a TRITONBACKEND_Request object using
+ * TRITONBACKEND_ResponseNew(). A response factory allows a request
+ * to be released before all responses have been sent. Releasing a
+ * request as early as possible releases all input tensor data and
+ * therefore may be desirable in some cases.
+
+ * Create the response factory associated with a request.
+ *
+ * @param factory Returns the new response factory.
+ * @param request The inference request.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseFactoryNew(
+ @Cast("TRITONBACKEND_ResponseFactory**") PointerPointer factory, TRITONBACKEND_Request request);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseFactoryNew(
+ @ByPtrPtr TRITONBACKEND_ResponseFactory factory, TRITONBACKEND_Request request);
+
+/** Destroy a response factory.
+ *
+ * @param factory The response factory.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseFactoryDelete(
+ TRITONBACKEND_ResponseFactory factory);
+
+/** Send response flags without a corresponding response.
+ *
+ * @param factory The response factory.
+ * @param send_flags Flags to send. @see
+ * TRITONSERVER_ResponseCompleteFlag. @see
+ * TRITONSERVER_InferenceResponseCompleteFn_t.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseFactorySendFlags(
+ TRITONBACKEND_ResponseFactory factory, @Cast("const uint32_t") int send_flags);
+
+/**
+ * TRITONBACKEND_Response
+ *
+ * Object representing an inference response. For a given request,
+ * the backend must carefully manage the lifecycle of responses
+ * generated for that request to ensure that the output tensor
+ * buffers are allocated correctly. When a response is created with
+ * TRITONBACKEND_ResponseNew or TRITONBACKEND_ResponseNewFromFactory,
+ * all the outputs and corresponding buffers must be created for that
+ * response using TRITONBACKEND_ResponseOutput and
+ * TRITONBACKEND_OutputBuffer *before* another response is created
+ * for the request. For a given response, outputs can be created in
+ * any order but they must be created sequentially/sychronously (for
+ * example, the backend cannot use multiple threads to simultaneously
+ * add multiple outputs to a response).
+ *
+ * The above requirement applies only to responses being generated
+ * for a given request. The backend may generate responses in
+ * parallel on multiple threads as long as those responses are for
+ * different requests.
+ *
+ * This order of response creation must be strictly followed. But,
+ * once response(s) are created they do not need to be sent
+ * immediately, nor do they need to be sent in the order they were
+ * created. The backend may even delete a created response instead of
+ * sending it by using TRITONBACKEND_ResponseDelete.
+
+ * Create a response for a request.
+ *
+ * @param response Returns the new response.
+ * @param request The request.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseNew(
+ @Cast("TRITONBACKEND_Response**") PointerPointer response, TRITONBACKEND_Request request);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseNew(
+ @ByPtrPtr TRITONBACKEND_Response response, TRITONBACKEND_Request request);
+
+/** Create a response using a factory.
+ *
+ * @param response Returns the new response.
+ * @param factory The response factory.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseNewFromFactory(
+ @Cast("TRITONBACKEND_Response**") PointerPointer response, TRITONBACKEND_ResponseFactory factory);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseNewFromFactory(
+ @ByPtrPtr TRITONBACKEND_Response response, TRITONBACKEND_ResponseFactory factory);
+
+/** Destroy a response. It is not necessary to delete a response if
+ * TRITONBACKEND_ResponseSend is called as that function transfers
+ * ownership of the response object to Triton.
+ *
+ * @param response The response.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseDelete(
+ TRITONBACKEND_Response response);
+
+/** Set a string parameter in the response.
+ *
+ * @param response The response.
+ * @param name The name of the parameter.
+ * @param value The value of the parameter.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSetStringParameter(
+ TRITONBACKEND_Response response, String name, String value);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSetStringParameter(
+ TRITONBACKEND_Response response, @Cast("const char*") BytePointer name, @Cast("const char*") BytePointer value);
+
+/** Set an integer parameter in the response.
+ *
+ * @param response The response.
+ * @param name The name of the parameter.
+ * @param value The value of the parameter.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSetIntParameter(
+ TRITONBACKEND_Response response, String name, @Cast("const int64_t") long value);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSetIntParameter(
+ TRITONBACKEND_Response response, @Cast("const char*") BytePointer name, @Cast("const int64_t") long value);
+
+/** Set an boolean parameter in the response.
+ *
+ * @param response The response.
+ * @param name The name of the parameter.
+ * @param value The value of the parameter.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSetBoolParameter(
+ TRITONBACKEND_Response response, String name, @Cast("const bool") boolean value);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSetBoolParameter(
+ TRITONBACKEND_Response response, @Cast("const char*") BytePointer name, @Cast("const bool") boolean value);
+
+/** Create an output tensor in the response. The lifetime of the
+ * returned output tensor object matches that of the response and so
+ * the output tensor object should not be accessed after the response
+ * object is deleted.
+ *
+ * @param response The response.
+ * @param output Returns the new response output.
+ * @param name The name of the output tensor.
+ * @param datatype The datatype of the output tensor.
+ * @param shape The shape of the output tensor.
+ * @param dims_count The number of dimensions in the output tensor
+ * shape.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @Cast("TRITONBACKEND_Output**") PointerPointer output,
+ String name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") LongPointer shape, @Cast("const uint32_t") int dims_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @ByPtrPtr TRITONBACKEND_Output output,
+ String name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") LongPointer shape, @Cast("const uint32_t") int dims_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @ByPtrPtr TRITONBACKEND_Output output,
+ @Cast("const char*") BytePointer name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") LongBuffer shape, @Cast("const uint32_t") int dims_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @ByPtrPtr TRITONBACKEND_Output output,
+ String name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") long[] shape, @Cast("const uint32_t") int dims_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @ByPtrPtr TRITONBACKEND_Output output,
+ @Cast("const char*") BytePointer name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") LongPointer shape, @Cast("const uint32_t") int dims_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @ByPtrPtr TRITONBACKEND_Output output,
+ String name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") LongBuffer shape, @Cast("const uint32_t") int dims_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseOutput(
+ TRITONBACKEND_Response response, @ByPtrPtr TRITONBACKEND_Output output,
+ @Cast("const char*") BytePointer name, @Cast("const TRITONSERVER_DataType") int datatype,
+ @Cast("const int64_t*") long[] shape, @Cast("const uint32_t") int dims_count);
+
+/** Send a response. Calling this function transfers ownership of the
+ * response object to Triton. The caller must not access or delete
+ * the response object after calling this function.
+ *
+ * @param response The response.
+ * @param send_flags Flags associated with the response. @see
+ * TRITONSERVER_ResponseCompleteFlag. @see
+ * TRITONSERVER_InferenceResponseCompleteFn_t.
+ * @param error The TRITONSERVER_Error to send if the response is an
+ * error, or nullptr if the response is successful.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ResponseSend(
+ TRITONBACKEND_Response response, @Cast("const uint32_t") int send_flags,
+ TRITONSERVER_Error error);
+
+/**
+ * TRITONBACKEND_Backend
+ *
+ * Object representing a backend.
+ *
+
+ * TRITONBACKEND_ExecutionPolicy
+ *
+ * Types of execution policy that can be implemented by a backend.
+ *
+ * TRITONBACKEND_EXECUTION_BLOCKING: An instance of the model
+ * blocks in TRITONBACKEND_ModelInstanceExecute until it is ready
+ * to handle another inference. Upon returning from
+ * TRITONBACKEND_ModelInstanceExecute, Triton may immediately
+ * call TRITONBACKEND_ModelInstanceExecute for the same instance
+ * to execute a new batch of requests. Thus, most backends using
+ * this policy will not return from
+ * TRITONBACKEND_ModelInstanceExecute until all responses have
+ * been sent and all requests have been released. This is the
+ * default execution policy.
+ *
+ * TRITONBACKEND_EXECUTION_DEVICE_BLOCKING: An instance, A, of the
+ * model blocks in TRITONBACKEND_ModelInstanceExecute if the
+ * device associated with the instance is unable to handle
+ * another inference. Even if another instance, B, associated
+ * with the device, is available and ready to perform an
+ * inference, Triton will not invoke
+ * TRITONBACKEND_ModeInstanceExecute for B until A returns from
+ * TRITONBACKEND_ModelInstanceExecute. Triton will not be blocked
+ * from calling TRITONBACKEND_ModelInstanceExecute for instance
+ * C, which is associated with a different device than A and B,
+ * even if A or B has not returned from
+ * TRITONBACKEND_ModelInstanceExecute. This execution policy is
+ * typically used by a backend that can cooperatively execute
+ * multiple model instances on the same device.
+ * */
+/** enum TRITONBACKEND_ExecutionPolicy */
+public static final int
+ TRITONBACKEND_EXECUTION_BLOCKING = 0,
+ TRITONBACKEND_EXECUTION_DEVICE_BLOCKING = 1;
+
+/** Get the name of the backend. The caller does not own the returned
+ * string and must not modify or delete it. The lifetime of the
+ * returned string extends only as long as 'backend'.
+ *
+ * @param backend The backend.
+ * @param name Returns the name of the backend.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_BackendName(
+ TRITONBACKEND_Backend backend, @Cast("const char**") PointerPointer name);
+public static native TRITONSERVER_Error TRITONBACKEND_BackendName(
+ TRITONBACKEND_Backend backend, @Cast("const char**") @ByPtrPtr BytePointer name);
+public static native TRITONSERVER_Error TRITONBACKEND_BackendName(
+ TRITONBACKEND_Backend backend, @Cast("const char**") @ByPtrPtr ByteBuffer name);
+public static native TRITONSERVER_Error TRITONBACKEND_BackendName(
+ TRITONBACKEND_Backend backend, @Cast("const char**") @ByPtrPtr byte[] name);
+
+/** Get the backend configuration. The 'backend_config' message is
+ * owned by Triton and should not be modified or freed by the caller.
+ *
+ * The backend configuration, as JSON, is:
+ *
+ * {
+ * "cmdline" : {
+ * "
+ * Get the name of the model. The returned string is owned by the
+ * model object, not the caller, and so should not be modified or
+ * freed.
+ *
+ * @param model The model.
+ * @param name Returns the model name.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelName(
+ TRITONBACKEND_Model model, @Cast("const char**") PointerPointer name);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelName(
+ TRITONBACKEND_Model model, @Cast("const char**") @ByPtrPtr BytePointer name);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelName(
+ TRITONBACKEND_Model model, @Cast("const char**") @ByPtrPtr ByteBuffer name);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelName(
+ TRITONBACKEND_Model model, @Cast("const char**") @ByPtrPtr byte[] name);
+
+/** Get the version of the model.
+ *
+ * @param model The model.
+ * @param version Returns the model version.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelVersion(
+ TRITONBACKEND_Model model, @Cast("uint64_t*") LongPointer version);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelVersion(
+ TRITONBACKEND_Model model, @Cast("uint64_t*") LongBuffer version);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelVersion(
+ TRITONBACKEND_Model model, @Cast("uint64_t*") long[] version);
+
+/** Get the location of the files that make up the model. The
+ * 'location' communicated depends on how the model is being
+ * communicated to Triton as indicated by 'artifact_type'.
+ *
+ * TRITONBACKEND_ARTIFACT_FILESYSTEM: The model artifacts are made
+ * available to Triton via the local filesytem. 'location'
+ * returns the full path to the directory in the model repository
+ * that contains this model's artifacts. The returned string is
+ * owned by Triton, not the caller, and so should not be modified
+ * or freed.
+ *
+ * @param model The model.
+ * @param artifact_type Returns the artifact type for the model.
+ * @param path Returns the location.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelRepository(
+ TRITONBACKEND_Model model, @Cast("TRITONBACKEND_ArtifactType*") IntPointer artifact_type,
+ @Cast("const char**") PointerPointer location);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelRepository(
+ TRITONBACKEND_Model model, @Cast("TRITONBACKEND_ArtifactType*") IntPointer artifact_type,
+ @Cast("const char**") @ByPtrPtr BytePointer location);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelRepository(
+ TRITONBACKEND_Model model, @Cast("TRITONBACKEND_ArtifactType*") IntBuffer artifact_type,
+ @Cast("const char**") @ByPtrPtr ByteBuffer location);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelRepository(
+ TRITONBACKEND_Model model, @Cast("TRITONBACKEND_ArtifactType*") int[] artifact_type,
+ @Cast("const char**") @ByPtrPtr byte[] location);
+
+/** Get the model configuration. The caller takes ownership of the
+ * message object and must call TRITONSERVER_MessageDelete to release
+ * the object. The configuration is available via this call even
+ * before the model is loaded and so can be used in
+ * TRITONBACKEND_ModelInitialize. TRITONSERVER_ServerModelConfig
+ * returns equivalent information but is not useable until after the
+ * model loads.
+ *
+ * @param model The model.
+ * @param config_version The model configuration will be returned in
+ * a format matching this version. If the configuration cannot be
+ * represented in the requested version's format then an error will
+ * be returned. Currently only version 1 is supported.
+ * @param model_config Returns the model configuration as a message.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelConfig(
+ TRITONBACKEND_Model model, @Cast("const uint32_t") int config_version,
+ @Cast("TRITONSERVER_Message**") PointerPointer model_config);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelConfig(
+ TRITONBACKEND_Model model, @Cast("const uint32_t") int config_version,
+ @ByPtrPtr TRITONSERVER_Message model_config);
+
+/** Whether the backend should attempt to auto-complete the model configuration.
+ * If true, the model should fill the inputs, outputs, and max batch size in
+ * the model configuration if incomplete. If the model configuration is
+ * changed, the new configuration must be reported to Triton using
+ * TRITONBACKEND_ModelSetConfig.
+ *
+ * @param model The model.
+ * @param auto_complete_config Returns whether the backend should auto-complete
+ * the model configuration.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelAutoCompleteConfig(
+ TRITONBACKEND_Model model, @Cast("bool*") boolean[] auto_complete_config);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelAutoCompleteConfig(
+ TRITONBACKEND_Model model, @Cast("bool*") BoolPointer auto_complete_config);
+
+/** Set the model configuration in Triton server. Only the inputs, outputs,
+ * and max batch size can be changed. Any other changes to the model
+ * configuration will be ignored by Triton. This function can only be called
+ * from TRITONBACKEND_ModelInitialize, calling in any other context will result
+ * in an error being returned. The function does not take ownership of the
+ * message object and so the caller should call TRITONSERVER_MessageDelete to
+ * release the object once the function returns.
+ *
+ * @param model The model.
+ * @param config_version The format version of the model configuration.
+ * If the configuration is not represented in the version's format
+ * then an error will be returned. Currently only version 1 is supported.
+ * @param model_config The updated model configuration as a message.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelSetConfig(
+ TRITONBACKEND_Model model, @Cast("const uint32_t") int config_version,
+ TRITONSERVER_Message model_config);
+
+/** Get the TRITONSERVER_Server object that this model is being served
+ * by.
+ *
+ * @param model The model.
+ * @param server Returns the server.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelServer(
+ TRITONBACKEND_Model model, @Cast("TRITONSERVER_Server**") PointerPointer server);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelServer(
+ TRITONBACKEND_Model model, @ByPtrPtr TRITONSERVER_Server server);
+
+/** Get the backend used by the model.
+ *
+ * @param model The model.
+ * @param model Returns the backend object.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelBackend(
+ TRITONBACKEND_Model model, @Cast("TRITONBACKEND_Backend**") PointerPointer backend);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelBackend(
+ TRITONBACKEND_Model model, @ByPtrPtr TRITONBACKEND_Backend backend);
+
+/** Get the user-specified state associated with the model. The
+ * state is completely owned and managed by the backend.
+ *
+ * @param model The model.
+ * @param state Returns the user state, or nullptr if no user state.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelState(
+ TRITONBACKEND_Model model, @Cast("void**") PointerPointer state);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelState(
+ TRITONBACKEND_Model model, @Cast("void**") @ByPtrPtr Pointer state);
+
+/** Set the user-specified state associated with the model. The
+ * state is completely owned and managed by the backend.
+ *
+ * @param model The model.
+ * @param state The user state, or nullptr if no user state.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+
+///
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelSetState(
+ TRITONBACKEND_Model model, Pointer state);
+
+/**
+ * TRITONBACKEND_ModelInstance
+ *
+ * Object representing a model instance implemented using the
+ * backend.
+ *
+
+ * Get the name of the model instance. The returned string is owned by the
+ * model object, not the caller, and so should not be modified or
+ * freed.
+ *
+ * @param instance The model instance.
+ * @param name Returns the instance name.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceName(
+ TRITONBACKEND_ModelInstance instance, @Cast("const char**") PointerPointer name);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceName(
+ TRITONBACKEND_ModelInstance instance, @Cast("const char**") @ByPtrPtr BytePointer name);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceName(
+ TRITONBACKEND_ModelInstance instance, @Cast("const char**") @ByPtrPtr ByteBuffer name);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceName(
+ TRITONBACKEND_ModelInstance instance, @Cast("const char**") @ByPtrPtr byte[] name);
+
+/** Get the kind of the model instance.
+ *
+ * @param instance The model instance.
+ * @param kind Returns the instance kind.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceKind(
+ TRITONBACKEND_ModelInstance instance,
+ @Cast("TRITONSERVER_InstanceGroupKind*") IntPointer kind);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceKind(
+ TRITONBACKEND_ModelInstance instance,
+ @Cast("TRITONSERVER_InstanceGroupKind*") IntBuffer kind);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceKind(
+ TRITONBACKEND_ModelInstance instance,
+ @Cast("TRITONSERVER_InstanceGroupKind*") int[] kind);
+
+/** Get the device ID of the model instance.
+ *
+ * @param instance The model instance.
+ * @param device_id Returns the instance device ID.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceDeviceId(
+ TRITONBACKEND_ModelInstance instance, IntPointer device_id);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceDeviceId(
+ TRITONBACKEND_ModelInstance instance, IntBuffer device_id);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceDeviceId(
+ TRITONBACKEND_ModelInstance instance, int[] device_id);
+
+/** Get the host policy setting. The 'host_policy' message is
+ * owned by Triton and should not be modified or freed by the caller.
+ *
+ * The host policy setting, as JSON, is:
+ *
+ * {
+ * "
+ * Initialize a backend. This function is optional, a backend is not
+ * required to implement it. This function is called once when a
+ * backend is loaded to allow the backend to initialize any state
+ * associated with the backend. A backend has a single state that is
+ * shared across all models that use the backend.
+ *
+ * @param backend The backend.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_Initialize(
+ TRITONBACKEND_Backend backend);
+
+/** Finalize for a backend. This function is optional, a backend is
+ * not required to implement it. This function is called once, just
+ * before the backend is unloaded. All state associated with the
+ * backend should be freed and any threads created for the backend
+ * should be exited/joined before returning from this function.
+ *
+ * @param backend The backend.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_Finalize(
+ TRITONBACKEND_Backend backend);
+
+/** Initialize for a model. This function is optional, a backend is
+ * not required to implement it. This function is called once when a
+ * model that uses the backend is loaded to allow the backend to
+ * initialize any state associated with the model. The backend should
+ * also examine the model configuration to determine if the
+ * configuration is suitable for the backend. Any errors reported by
+ * this function will prevent the model from loading.
+ *
+ * @param model The model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInitialize(
+ TRITONBACKEND_Model model);
+
+/** Finalize for a model. This function is optional, a backend is not
+ * required to implement it. This function is called once for a
+ * model, just before the model is unloaded from Triton. All state
+ * associated with the model should be freed and any threads created
+ * for the model should be exited/joined before returning from this
+ * function.
+ *
+ * @param model The model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelFinalize(
+ TRITONBACKEND_Model model);
+
+/** Initialize for a model instance. This function is optional, a
+ * backend is not required to implement it. This function is called
+ * once when a model instance is created to allow the backend to
+ * initialize any state associated with the instance.
+ *
+ * @param instance The model instance.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceInitialize(
+ TRITONBACKEND_ModelInstance instance);
+
+/** Finalize for a model instance. This function is optional, a
+ * backend is not required to implement it. This function is called
+ * once for an instance, just before the corresponding model is
+ * unloaded from Triton. All state associated with the instance
+ * should be freed and any threads created for the instance should be
+ * exited/joined before returning from this function.
+ *
+ * @param instance The model instance.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceFinalize(
+ TRITONBACKEND_ModelInstance instance);
+
+/** Execute a batch of one or more requests on a model instance. This
+ * function is required. Triton will not perform multiple
+ * simultaneous calls to this function for a given model 'instance';
+ * however, there may be simultaneous calls for different model
+ * instances (for the same or different models).
+ *
+ * If an error is returned the ownership of the request objects
+ * remains with Triton and the backend must not retain references to
+ * the request objects or access them in any way.
+ *
+ * If success is returned, ownership of the request objects is
+ * transferred to the backend and it is then responsible for creating
+ * responses and releasing the request objects. Note that even though
+ * ownership of the request objects is transferred to the backend, the
+ * ownership of the buffer holding request pointers is returned back
+ * to Triton upon return from TRITONBACKEND_ModelInstanceExecute. If
+ * any request objects need to be maintained beyond
+ * TRITONBACKEND_ModelInstanceExecute, then the pointers must be copied
+ * out of the array within TRITONBACKEND_ModelInstanceExecute.
+ *
+ * @param instance The model instance.
+ * @param requests The requests.
+ * @param request_count The number of requests in the batch.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceExecute(
+ TRITONBACKEND_ModelInstance instance, @Cast("TRITONBACKEND_Request**") PointerPointer requests,
+ @Cast("const uint32_t") int request_count);
+public static native TRITONSERVER_Error TRITONBACKEND_ModelInstanceExecute(
+ TRITONBACKEND_ModelInstance instance, @ByPtrPtr TRITONBACKEND_Request requests,
+ @Cast("const uint32_t") int request_count);
+
+
+// #ifdef __cplusplus
+// #endif
+
+
+// Parsed from tritonrepoagent.h
+
+// Copyright (c) 2020-2021, NVIDIA CORPORATION. All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions
+// are met:
+// * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+// * Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the distribution.
+// * Neither the name of NVIDIA CORPORATION nor the names of its
+// contributors may be used to endorse or promote products derived
+// from this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+// #pragma once
+
+// #include
+ * Initialize an agent. This function is optional. This function is
+ * called once when an agent is loaded to allow the agent to
+ * initialize any state associated with the agent. An agent has a
+ * single state that is shared across all invocations of the agent.
+ *
+ * @param agent The agent.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONREPOAGENT_Initialize(
+ TRITONREPOAGENT_Agent agent);
+
+/** Finalize for an agent. This function is optional. This function is
+ * called once, just before the agent is unloaded. All state
+ * associated with the agent should be freed and any threads created
+ * for the agent should be exited/joined before returning from this
+ * function.
+ *
+ * @param agent The agent.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONREPOAGENT_Finalize(
+ TRITONREPOAGENT_Agent agent);
+
+/** Initialize a model associated with an agent. This function is optional.
+ * This function is called once when an agent model's lifecycle begins to allow
+ * the agent model to initialize any state associated with it. An agent model
+ * has a single state that is shared across all the lifecycle of the agent
+ * model.
+ *
+ * @param agent The agent to be associated with the model.
+ * @param model The model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+public static native TRITONSERVER_Error TRITONREPOAGENT_ModelInitialize(
+ TRITONREPOAGENT_Agent agent, TRITONREPOAGENT_AgentModel model);
+
+/** Finalize for a model. This function is optional. This function is
+ * called once, just before the end of the agent model's lifecycle. All state
+ * associated with the agent model should be freed and any threads created
+ * for the agent model should be exited/joined before returning from this
+ * function. If the model acquired a model location using
+ * TRITONREPOAGENT_ModelRepositoryLocationAcquire, it must call
+ * TRITONREPOAGENT_ModelRepositoryLocationRelease to release that location.
+ *
+ * @param agent The agent associated with the model.
+ * @param model The model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+
+///
+///
+///
+public static native TRITONSERVER_Error TRITONREPOAGENT_ModelFinalize(
+ TRITONREPOAGENT_Agent agent, TRITONREPOAGENT_AgentModel model);
+
+/** Handle an action for a specified model. This function is
+ * required. Triton will not perform multiple simultaneous calls to
+ * this function for a given agent and model; however, there may be
+ * simultaneous calls for the agent for different models.
+ *
+ * If the agent does not handle the action the agent should
+ * immediately return success (nullptr).
+ *
+ * Any modification to the model's repository must be made when 'action_type'
+ * is TRITONREPOAGENT_ACTION_LOAD.
+ * To modify the model's repository the agent must either acquire a mutable
+ * location via TRITONREPOAGENT_ModelRepositoryLocationAcquire
+ * or its own managed location, report the location to Triton via
+ * TRITONREPOAGENT_ModelRepositoryUpdate, and then return
+ * success (nullptr). If the agent does not need to make any changes
+ * to the model repository it should not call
+ * TRITONREPOAGENT_ModelRepositoryUpdate and then return success.
+ * To indicate that a model load should fail return a non-success status.
+ *
+ * @param agent The agent.
+ * @param model The model that is the target of the action.
+ * \action_type The type of action the agent should handle for the model.
+ * @return a TRITONSERVER_Error indicating success or failure. */
+public static native TRITONSERVER_Error TRITONREPOAGENT_ModelAction(
+ TRITONREPOAGENT_Agent agent, TRITONREPOAGENT_AgentModel model,
+ @Cast("const TRITONREPOAGENT_ActionType") int action_type);
+
+// #ifdef __cplusplus
+// #endif
+
+
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Backend.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Backend.java
new file mode 100644
index 00000000000..f67238a4484
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Backend.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_Backend extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_Backend() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_Backend(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Input.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Input.java
new file mode 100644
index 00000000000..d5733453fef
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Input.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_Input extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_Input() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_Input(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_MemoryManager.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_MemoryManager.java
new file mode 100644
index 00000000000..365b5f33ab6
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_MemoryManager.java
@@ -0,0 +1,38 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+// #endif
+// #endif
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_MemoryManager extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_MemoryManager() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_MemoryManager(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Model.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Model.java
new file mode 100644
index 00000000000..900f251464f
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Model.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_Model extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_Model() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_Model(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_ModelInstance.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_ModelInstance.java
new file mode 100644
index 00000000000..66fbfbf7901
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_ModelInstance.java
@@ -0,0 +1,41 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+
+///
+///
+///
+///
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_ModelInstance extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_ModelInstance() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_ModelInstance(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Output.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Output.java
new file mode 100644
index 00000000000..83fa1b7d53a
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Output.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_Output extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_Output() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_Output(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Request.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Request.java
new file mode 100644
index 00000000000..d8a5e96510c
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Request.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_Request extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_Request() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_Request(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Response.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Response.java
new file mode 100644
index 00000000000..9acbf56eb49
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_Response.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_Response extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_Response() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_Response(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_ResponseFactory.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_ResponseFactory.java
new file mode 100644
index 00000000000..bdecf0e62bb
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONBACKEND_ResponseFactory.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONBACKEND_ResponseFactory extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONBACKEND_ResponseFactory() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONBACKEND_ResponseFactory(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONREPOAGENT_Agent.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONREPOAGENT_Agent.java
new file mode 100644
index 00000000000..dec4c76ade6
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONREPOAGENT_Agent.java
@@ -0,0 +1,38 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+// #endif
+// #endif
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONREPOAGENT_Agent extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONREPOAGENT_Agent() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONREPOAGENT_Agent(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONREPOAGENT_AgentModel.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONREPOAGENT_AgentModel.java
new file mode 100644
index 00000000000..e1a494c1036
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONREPOAGENT_AgentModel.java
@@ -0,0 +1,41 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+
+///
+///
+///
+///
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONREPOAGENT_AgentModel extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONREPOAGENT_AgentModel() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONREPOAGENT_AgentModel(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Error.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Error.java
new file mode 100644
index 00000000000..f8774fc5b6a
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Error.java
@@ -0,0 +1,38 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+// #endif
+// #endif
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_Error extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_Error() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_Error(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceRequest.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceRequest.java
new file mode 100644
index 00000000000..30c463566b9
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceRequest.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceRequest extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_InferenceRequest() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceRequest(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceRequestReleaseFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceRequestReleaseFn_t.java
new file mode 100644
index 00000000000..a35db367e31
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceRequestReleaseFn_t.java
@@ -0,0 +1,64 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** Type for inference request release callback function. The callback
+ * indicates what type of release is being performed on the request
+ * and for some of these the callback function takes ownership of the
+ * TRITONSERVER_InferenceRequest object. The 'userp' data is the data
+ * provided as 'request_release_userp' in the call to
+ * TRITONSERVER_InferenceRequestSetReleaseCallback.
+ *
+ * One or more flags will be specified when the callback is invoked,
+ * and the callback must take the following actions:
+ *
+ * - TRITONSERVER_REQUEST_RELEASE_ALL: The entire inference request
+ * is being released and ownership is passed to the callback
+ * function. Triton will not longer access the 'request' object
+ * itself nor any input tensor data associated with the
+ * request. The callback should free or otherwise manage the
+ * 'request' object and all associated tensor data.
+ *
+ * Note that currently TRITONSERVER_REQUEST_RELEASE_ALL should always
+ * be set when the callback is invoked but in the future that may
+ * change, so the callback should explicitly check for the flag
+ * before taking ownership of the request object.
+ * */
+
+///
+///
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceRequestReleaseFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceRequestReleaseFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_InferenceRequestReleaseFn_t() { allocate(); }
+ private native void allocate();
+ public native void call(
+ TRITONSERVER_InferenceRequest request, @Cast("const uint32_t") int flags, Pointer userp);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceResponse.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceResponse.java
new file mode 100644
index 00000000000..6f28a7329b3
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceResponse.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceResponse extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_InferenceResponse() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceResponse(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceResponseCompleteFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceResponseCompleteFn_t.java
new file mode 100644
index 00000000000..0e964d3b075
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceResponseCompleteFn_t.java
@@ -0,0 +1,59 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** Type for callback function indicating that an inference response
+ * has completed. The callback function takes ownership of the
+ * TRITONSERVER_InferenceResponse object. The 'userp' data is the
+ * data provided as 'response_userp' in the call to
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ *
+ * One or more flags may be specified when the callback is invoked:
+ *
+ * - TRITONSERVER_RESPONSE_COMPLETE_FINAL: Indicates that no more
+ * responses will be generated for a given request (more
+ * specifically, that no more responses will be generated for the
+ * inference request that set this callback and 'userp'). When
+ * this flag is set 'response' may be a response object or may be
+ * nullptr. If 'response' is not nullptr, then 'response' is the
+ * last response that Triton will produce for the request. If
+ * 'response' is nullptr then Triton is indicating that no more
+ * responses will be produced for the request. */
+
+///
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceResponseCompleteFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceResponseCompleteFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_InferenceResponseCompleteFn_t() { allocate(); }
+ private native void allocate();
+ public native void call(
+ TRITONSERVER_InferenceResponse response, @Cast("const uint32_t") int flags,
+ Pointer userp);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTrace.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTrace.java
new file mode 100644
index 00000000000..9cd501b42ba
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTrace.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceTrace extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_InferenceTrace() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceTrace(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTraceActivityFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTraceActivityFn_t.java
new file mode 100644
index 00000000000..38cae917a28
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTraceActivityFn_t.java
@@ -0,0 +1,47 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** Type for trace activity callback function. This callback function
+ * is used to report activity occurring for a trace. This function
+ * does not take ownership of 'trace' and so any information needed
+ * from that object must be copied before returning. The 'userp' data
+ * is the same as what is supplied in the call to
+ * TRITONSERVER_InferenceTraceNew. */
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceTraceActivityFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceTraceActivityFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_InferenceTraceActivityFn_t() { allocate(); }
+ private native void allocate();
+ public native void call(
+ TRITONSERVER_InferenceTrace trace,
+ @Cast("TRITONSERVER_InferenceTraceActivity") int activity, @Cast("uint64_t") long timestamp_ns,
+ Pointer userp);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTraceReleaseFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTraceReleaseFn_t.java
new file mode 100644
index 00000000000..ef311def896
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_InferenceTraceReleaseFn_t.java
@@ -0,0 +1,48 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** Type for trace release callback function. This callback function
+ * is called when all activity for the trace has completed. The
+ * callback function takes ownership of the
+ * TRITONSERVER_InferenceTrace object. The 'userp' data is the same
+ * as what is supplied in the call to TRITONSERVER_InferenceTraceNew. */
+
+///
+///
+///
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_InferenceTraceReleaseFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_InferenceTraceReleaseFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_InferenceTraceReleaseFn_t() { allocate(); }
+ private native void allocate();
+ public native void call(
+ TRITONSERVER_InferenceTrace trace, Pointer userp);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Message.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Message.java
new file mode 100644
index 00000000000..fd1a25c8413
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Message.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_Message extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_Message() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_Message(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Metrics.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Metrics.java
new file mode 100644
index 00000000000..e1a050cf843
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Metrics.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_Metrics extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_Metrics() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_Metrics(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocator.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocator.java
new file mode 100644
index 00000000000..01449657612
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocator.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_ResponseAllocator extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_ResponseAllocator() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_ResponseAllocator(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorAllocFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorAllocFn_t.java
new file mode 100644
index 00000000000..ede55743410
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorAllocFn_t.java
@@ -0,0 +1,81 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** TRITONSERVER_ResponseAllocator
+ *
+ * Object representing a memory allocator for output tensors in an
+ * inference response.
+ *
+
+ * Type for allocation function that allocates a buffer to hold an
+ * output tensor.
+ *
+ * @param allocator The allocator that is provided in the call to
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ * @param tensor_name The name of the output tensor to allocate for.
+ * @param byte_size The size of the buffer to allocate.
+ * @param memory_type The type of memory that the caller prefers for
+ * the buffer allocation.
+ * @param memory_type_id The ID of the memory that the caller prefers
+ * for the buffer allocation.
+ * @param userp The user data pointer that is provided as
+ * 'response_allocator_userp' in the call to
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ * @param buffer Returns a pointer to the allocated memory.
+ * @param buffer_userp Returns a user-specified value to associate
+ * with the buffer, or nullptr if no user-specified value should be
+ * associated with the buffer. This value will be provided in the
+ * call to TRITONSERVER_ResponseAllocatorReleaseFn_t when the buffer
+ * is released and will also be returned by
+ * TRITONSERVER_InferenceResponseOutput.
+ * @param actual_memory_type Returns the type of memory where the
+ * allocation resides. May be different than the type of memory
+ * requested by 'memory_type'.
+ * @param actual_memory_type_id Returns the ID of the memory where
+ * the allocation resides. May be different than the ID of the memory
+ * requested by 'memory_type_id'.
+ * @return a TRITONSERVER_Error object if a failure occurs while
+ * attempting an allocation. If an error is returned all other return
+ * values will be ignored. */
+
+///
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_ResponseAllocatorAllocFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_ResponseAllocatorAllocFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_ResponseAllocatorAllocFn_t() { allocate(); }
+ private native void allocate();
+ public native TRITONSERVER_Error call(
+ TRITONSERVER_ResponseAllocator allocator, String tensor_name,
+ @Cast("size_t") long byte_size, @Cast("TRITONSERVER_MemoryType") int memory_type,
+ @Cast("int64_t") long memory_type_id, Pointer userp, @Cast("void**") PointerPointer buffer, @Cast("void**") PointerPointer buffer_userp,
+ @Cast("TRITONSERVER_MemoryType*") IntPointer actual_memory_type,
+ @Cast("int64_t*") LongPointer actual_memory_type_id);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorReleaseFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorReleaseFn_t.java
new file mode 100644
index 00000000000..eaa984d8f70
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorReleaseFn_t.java
@@ -0,0 +1,60 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** Type for function that is called when the server no longer holds
+ * any reference to a buffer allocated by
+ * TRITONSERVER_ResponseAllocatorAllocFn_t. In practice this function
+ * is typically called when the response object associated with the
+ * buffer is deleted by TRITONSERVER_InferenceResponseDelete.
+ *
+ * @param allocator The allocator that is provided in the call to
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ * @param buffer Pointer to the buffer to be freed.
+ * @param buffer_userp The user-specified value associated
+ * with the buffer in TRITONSERVER_ResponseAllocatorAllocFn_t.
+ * @param byte_size The size of the buffer.
+ * @param memory_type The type of memory holding the buffer.
+ * @param memory_type_id The ID of the memory holding the buffer.
+ * @return a TRITONSERVER_Error object if a failure occurs while
+ * attempting the release. If an error is returned Triton will not
+ * attempt to release the buffer again. */
+
+///
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_ResponseAllocatorReleaseFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_ResponseAllocatorReleaseFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_ResponseAllocatorReleaseFn_t() { allocate(); }
+ private native void allocate();
+ public native TRITONSERVER_Error call(
+ TRITONSERVER_ResponseAllocator allocator, Pointer buffer, Pointer buffer_userp,
+ @Cast("size_t") long byte_size, @Cast("TRITONSERVER_MemoryType") int memory_type,
+ @Cast("int64_t") long memory_type_id);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorStartFn_t.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorStartFn_t.java
new file mode 100644
index 00000000000..62253b4bed1
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ResponseAllocatorStartFn_t.java
@@ -0,0 +1,55 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+/** Type for function that is called to indicate that subsequent
+ * allocation requests will refer to a new response.
+ *
+ * @param allocator The allocator that is provided in the call to
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ * @param userp The user data pointer that is provided as
+ * 'response_allocator_userp' in the call to
+ * TRITONSERVER_InferenceRequestSetResponseCallback.
+ * @return a TRITONSERVER_Error object if a failure occurs. */
+
+///
+///
+///
+///
+///
+///
+@Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_ResponseAllocatorStartFn_t extends FunctionPointer {
+ static { Loader.load(); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_ResponseAllocatorStartFn_t(Pointer p) { super(p); }
+ protected TRITONSERVER_ResponseAllocatorStartFn_t() { allocate(); }
+ private native void allocate();
+ public native TRITONSERVER_Error call(
+ TRITONSERVER_ResponseAllocator allocator, Pointer userp);
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Server.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Server.java
new file mode 100644
index 00000000000..ab656568bd4
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_Server.java
@@ -0,0 +1,35 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_Server extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_Server() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_Server(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ServerOptions.java b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ServerOptions.java
new file mode 100644
index 00000000000..4bb5d2c8892
--- /dev/null
+++ b/tritonserver/src/gen/java/org/bytedeco/tritonserver/tritonserver/TRITONSERVER_ServerOptions.java
@@ -0,0 +1,41 @@
+// Targeted by JavaCPP version 1.5.7-SNAPSHOT: DO NOT EDIT THIS FILE
+
+package org.bytedeco.tritonserver.tritonserver;
+
+import java.nio.*;
+import org.bytedeco.javacpp.*;
+import org.bytedeco.javacpp.annotation.*;
+
+import static org.bytedeco.javacpp.presets.javacpp.*;
+import org.bytedeco.cuda.cudart.*;
+import static org.bytedeco.cuda.global.cudart.*;
+import org.bytedeco.cuda.cublas.*;
+import static org.bytedeco.cuda.global.cublas.*;
+import org.bytedeco.cuda.cudnn.*;
+import static org.bytedeco.cuda.global.cudnn.*;
+import org.bytedeco.cuda.nvrtc.*;
+import static org.bytedeco.cuda.global.nvrtc.*;
+import org.bytedeco.tensorrt.nvinfer.*;
+import static org.bytedeco.tensorrt.global.nvinfer.*;
+import org.bytedeco.tensorrt.nvinfer_plugin.*;
+import static org.bytedeco.tensorrt.global.nvinfer_plugin.*;
+import org.bytedeco.tensorrt.nvonnxparser.*;
+import static org.bytedeco.tensorrt.global.nvonnxparser.*;
+import org.bytedeco.tensorrt.nvparsers.*;
+import static org.bytedeco.tensorrt.global.nvparsers.*;
+
+import static org.bytedeco.tritonserver.global.tritonserver.*;
+
+
+
+///
+///
+///
+///
+@Opaque @Properties(inherit = org.bytedeco.tritonserver.presets.tritonserver.class)
+public class TRITONSERVER_ServerOptions extends Pointer {
+ /** Empty constructor. Calls {@code super((Pointer)null)}. */
+ public TRITONSERVER_ServerOptions() { super((Pointer)null); }
+ /** Pointer cast constructor. Invokes {@link Pointer#Pointer(Pointer)}. */
+ public TRITONSERVER_ServerOptions(Pointer p) { super(p); }
+}
diff --git a/tritonserver/src/main/java/org/bytedeco/tritonserver/presets/tritonserver.java b/tritonserver/src/main/java/org/bytedeco/tritonserver/presets/tritonserver.java
new file mode 100644
index 00000000000..d8ab9a806b1
--- /dev/null
+++ b/tritonserver/src/main/java/org/bytedeco/tritonserver/presets/tritonserver.java
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2021 Jack He, Samuel Audet
+ *
+ * Licensed either under the Apache License, Version 2.0, or (at your option)
+ * under the terms of the GNU General Public License as published by
+ * the Free Software Foundation (subject to the "Classpath" exception),
+ * either version 2, or any later version (collectively, the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * http://www.gnu.org/licenses/
+ * http://www.gnu.org/software/classpath/license.html
+ *
+ * or as provided in the LICENSE.txt file that accompanied this code.
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.bytedeco.tritonserver.presets;
+
+import java.util.List;
+import org.bytedeco.javacpp.ClassProperties;
+import org.bytedeco.javacpp.LoadEnabled;
+import org.bytedeco.javacpp.Loader;
+import org.bytedeco.javacpp.annotation.Platform;
+import org.bytedeco.javacpp.annotation.Properties;
+import org.bytedeco.javacpp.tools.Info;
+import org.bytedeco.javacpp.tools.InfoMap;
+import org.bytedeco.javacpp.tools.InfoMapper;
+
+import org.bytedeco.cuda.presets.cudart;
+import org.bytedeco.cuda.presets.cublas;
+import org.bytedeco.cuda.presets.cudnn;
+import org.bytedeco.cuda.presets.nvrtc;
+import org.bytedeco.tensorrt.presets.nvinfer;
+import org.bytedeco.tensorrt.presets.nvinfer_plugin;
+import org.bytedeco.tensorrt.presets.nvonnxparser;
+import org.bytedeco.tensorrt.presets.nvparsers;
+
+/**
+ *
+ * @author Jack He
+ */
+@Properties(
+ inherit = {cublas.class, cudnn.class, nvrtc.class, nvinfer.class, nvinfer_plugin.class, nvonnxparser.class, nvparsers.class},
+ value = {
+ @Platform(
+ value = {"linux-arm64", "linux-ppc64le", "linux-x86_64", "windows-x86_64"},
+ include = {"tritonserver.h", "tritonbackend.h", "tritonrepoagent.h"},
+ exclude = {"