mooncake-transfer-engine

import numpy as np import os # In a real distributed setup, a metadata server (e.g., etcd) would be used. # For a simple local demo, 'P2PHANDSHAKE' can be used. METADATA_SERVER = os.environ.get('MC_METADATA_SERVER', 'P2PHANDSHAKE') LOCAL_HOSTNAME = os.environ.get('MC_LOCAL_HOSTNAME', '127.0.0.1:12345') PROTOCOL = os.environ.get('MC_PROTOCOL', 'tcp') # Use 'rdma' for RDMA-capable networks DEVICE_NAME = os.environ.get('MC_DEVICE_NAME', '') # Auto discovery if empty try: from mooncake.engine import TransferEngine # Create transfer engine instance engine = TransferEngine() # Initialize with basic configuration # In a real scenario, local_hostname would be the actual server IP/port # and metadata_server would point to the etcd cluster or similar. engine.initialize( LOCAL_HOSTNAME, METADATA_SERVER, PROTOCOL, DEVICE_NAME ) # Allocate and initialize a buffer (e.g., 1MB) # Note: For GPU memory, specific allocation methods/context would be needed. client_buffer = np.zeros(1024 * 1024, dtype=np.uint8) buffer_address = client_buffer.ctypes.data buffer_length = client_buffer.nbytes print(f"TransferEngine initialized on {LOCAL_HOSTNAME} with {PROTOCOL} protocol.") print(f"Allocated buffer at address: {buffer_address}, length: {buffer_length} bytes.") # Example: Register memory (optional, depending on protocol/usage) # engine.register_memory(buffer_address, buffer_length) # In a full setup, you would then perform transfer operations # e.g., engine.transfer_sync_write(target_hostname, buffer_address, peer_buffer_address, buffer_length) print("Mooncake Transfer Engine basic setup successful (no actual transfer performed).") except ImportError: print("mooncake-transfer-engine not installed or could not be imported.") print("Please ensure you installed the correct version for your CUDA environment.") except Exception as e: print(f"An error occurred: {e}")