# Note: Lot of the "host_" flags such as "host_cpu" and "host_crosstool_top"
# flags seem to be actually used to specify the execution platform details. It
# seems it is this way because these flags are old and predate the distinction
# between host and execution platform.
build:cross_compile_base --host_cpu=k8
build:cross_compile_base --host_crosstool_top=//tensorflow/tools/toolchains/cross_compile/cc:cross_compile_toolchain_suite

  * New SchedulerExtender enables users to implement custom
out-of-(the-scheduler)-process scheduling predicates and priority functions,
for example to schedule pods based on resources that are not directly managed

 * developers are saved from the hassles of encoding and decoding.
 *
 * ### Plus a modern API
 *
 * The URL (JDK1.0) and URI (Java 1.4) classes predate builders and instead use telescoping
 * constructors. For example, there's no API to compose a URI with a custom port without also
 * providing a query and fragment.
 *

* Add a new kubelet endpoint for serving first-class resource metrics ([#73946](https://github.com/kubernetes/kubernetes/pull/73946), [@dashpole](https://github.com/dashpole))
* Deprecate AWS, Azure, GCE and Cinder specific volume limit predicates. ([#74544](https://github.com/kubernetes/kubernetes/pull/74544), [@gnufied](https://github.com/gnufied))

//     Those cannot be well described when embedded.
//  3. Inconsistent validation.  Because the usages are different, the validation rules are different by usage, which makes it hard for users to predict what will happen.
//  4. The fields are both imprecise and overly precise.  Kind is not a precise mapping to a URL. This can produce ambiguity

    yield
    # Clean up the ML models and release the resources
    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.

binary, for any purpose, commercial or non-commercial, and by any
means.

In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and