large_constant]`) into 32-bit arithmetic in SASS.

    As a result, these versions of `ptxas` miscompile most XLA programs which
    use more than 4GB of temp memory. This results in garbage results and/or
    `CUDA_ERROR_ILLEGAL_ADDRESS` failures.

    A fix in CUDA 9.1.121 is expected in late February 2018. We do not expect a

iteration Result = Composite W = 41 B = 16 # End of iteration Result = Composite W = 41 B = 14 # End of iteration Result = Composite W = 41 B = 2 # End of iteration Result = Composite W = 41 B = 3a # End of iteration Result = Composite W = 55 B = 40 # End of iteration Result = Composite W = 55 B = 7 # End of iteration Result = Composite W = 55 B = 23 # End of iteration Result = Composite W = 55 B = 2e # End of iteration Result = Composite W = 55 B = 2a # W below is composite, but it is one of the...

    ml_models.clear()


app = FastAPI(lifespan=lifespan)


@app.get("/predict")
async def predict(x: float):
    result = ml_models["answer_to_everything"](x)
    return {"result": result}
```

**Note**: This is the recommended way going forward, instead of using `startup` and `shutdown` events.