tritonclient

import numpy as np import tritonclient.http as tritonhttp import os TRITON_SERVER_URL = os.environ.get('TRITON_SERVER_URL', 'localhost:8000') MODEL_NAME = 'simple_model' MODEL_VERSION = '1' INPUT_NAME = 'input_0' OUTPUT_NAME = 'output_0' def main(): try: # Create a Triton HTTP client client = tritonhttp.InferenceServerClient(url=TRITON_SERVER_URL) # Check server readiness if not client.is_server_ready(): print(f"Triton server at {TRITON_SERVER_URL} is not ready.") return print(f"Triton server at {TRITON_SERVER_URL} is ready.") # Prepare input data (e.g., a simple numpy array) input_data = np.random.rand(1, 16).astype(np.float32) # Create InferInput object infer_input = tritonhttp.InferInput(INPUT_NAME, input_data.shape, 'FP32') infer_input.set_data_from_numpy(input_data, binary_data=True) # Create InferRequestedOutput object infer_output = tritonhttp.InferRequestedOutput(OUTPUT_NAME, binary_data=True) # Send inference request response = client.infer( model_name=MODEL_NAME, inputs=[infer_input], outputs=[infer_output], model_version=MODEL_VERSION ) # Get output as numpy array output_data = response.as_numpy(OUTPUT_NAME) print(f"Inference successful! Output shape: {output_data.shape}") print(f"First 5 output values: {output_data.flatten()[:5]}") except Exception as e: print(f"An error occurred: {e}") if __name__ == '__main__': main()