INNER CODE UNIT · Python

_generate_complete

ai-infra-curriculum/ai-infra-engineer-learning · projects/project-103-llm-deployment/src/llm/server.py:222

    async def _generate_complete(
        self,
        prompt: str,
        sampling_params: Any
    ) -> str:
        """
        Internal method for complete generation.

        TODO: Implement non-streaming logic:
        1. Generate text synchronously
        2. Wait for complete response
        3. Extract and return final text
        4. Track latency metrics
        """
        # TODO: Implement complete generation
        # request_id = str(uuid.uuid4())
        # final_output = None
        # async for output in self.engine.generate(prompt, sampling_params, request_id):

View source record →