专家并行部署¶

from openai import OpenAI
import uuid

try:
    # 1: Set up clients for prefill and decode instances
    openai_api_key = "EMPTY"  # vLLM doesn't require a real API key

    # Replace these IP addresses with your actual instance addresses
    prefill_client = OpenAI(
        api_key=openai_api_key,
        base_url="http://192.168.1.100:8000/v1",  # Prefill instance URL
    )
    decode_client = OpenAI(
        api_key=openai_api_key,
        base_url="http://192.168.1.101:8001/v1",  # Decode instance URL  
    )

    # Get model name from prefill instance
    models = prefill_client.models.list()
    model = models.data[0].id
    print(f"Using model: {model}")

    # 2: Prefill Phase
    # Generate unique request ID to link prefill and decode operations
    request_id = str(uuid.uuid4())
    print(f"Request ID: {request_id}")

    prefill_response = prefill_client.completions.create(
        model=model,
        # Prompt must exceed vLLM's block size (16 tokens) for PD to work
        prompt="Write a detailed explanation of Paged Attention for Transformers works including the management of KV cache for multi-turn conversations",
        max_tokens=1,  # Force prefill-only operation
        extra_body={
            "kv_transfer_params": {
                "do_remote_decode": True,     # Enable remote decode
                "do_remote_prefill": False,   # This is the prefill instance
                "remote_engine_id": None,     # Will be populated by vLLM
                "remote_block_ids": None,     # Will be populated by vLLM
                "remote_host": None,          # Will be populated by vLLM
                "remote_port": None           # Will be populated by vLLM
            }
        },
        extra_headers={"X-Request-Id": request_id}
    )

    print("-" * 50)
    print("✓ Prefill completed successfully")
    print(f"Prefill response: {prefill_response.choices[0].text}")

    # 3: Decode Phase
    # Transfer KV cache parameters from prefill to decode instance
    decode_response = decode_client.completions.create(
        model=model,
        prompt="This prompt is ignored during decode",  # Original prompt not needed
        max_tokens=150,  # Generate up to 150 tokens
        extra_body={
            "kv_transfer_params": prefill_response.kv_transfer_params  # Pass KV cache info
        },
        extra_headers={"X-Request-Id": request_id}  # Same request ID
    )

    print("-" * 50)
    print("✓ Decode completed successfully")
    print(f"Final response: {decode_response.choices[0].text}")

except Exception as e:
    print(f"❌ Error during disaggregated serving: {e}")
    print("Check that both prefill and decode instances are running and accessible")