{
  input: {
    prompt: "A cute cat"
  }
}

{
  input: {
    prompt: "A cute cat"
  }
}

Error initializing vLLM engine: The model's max seq len (32768) is larger than the maximum number of tokens that can be stored in KV cache (24144). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.

Error initializing vLLM engine: The model's max seq len (32768) is larger than the maximum number of tokens that can be stored in KV cache (24144). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.

"concurrency_modifier": 4

"concurrency_modifier": 4

import runpod
import asyncio

async def async_generator_handler(job):
    for i in range(5):
        # Generate an asynchronous output token
        output = f"Generated async token output {i}"
        yield output

        # Simulate an asynchronous task, such as processing time for a large language model
        await asyncio.sleep(1)


# Configure and start the RunPod serverless function
runpod.serverless.start(
    {
        "handler": async_generator_handler,  # Required: Specify the async handler
        "return_aggregate_stream": True,  # Optional: Aggregate results are accessible via /run endpoint
    }
)

import runpod
import asyncio

async def async_generator_handler(job):
    for i in range(5):
        # Generate an asynchronous output token
        output = f"Generated async token output {i}"
        yield output

        # Simulate an asynchronous task, such as processing time for a large language model
        await asyncio.sleep(1)


# Configure and start the RunPod serverless function
runpod.serverless.start(
    {
        "handler": async_generator_handler,  # Required: Specify the async handler
        "return_aggregate_stream": True,  # Optional: Aggregate results are accessible via /run endpoint
    }
)