### Server Memory

For example, if your code loads a Machine Learning model with **1 GB in size**, when you run one process with your API, it will consume at least 1 GB of RAM. And if you start **4 processes** (4 workers), each will consume 1 GB of RAM. So in total, your API will consume **4 GB of RAM**.

And if your remote server or virtual machine only has 3 GB of RAM, trying to load more than 4 GB of RAM will cause problems. 🚨

github.com/go-openapi/loads v0.17.0/go.mod h1:72tmFy5wsWx89uEVddd0RjRWPZm92WRLhf7AC+0+OOU=
github.com/go-openapi/loads v0.18.0/go.mod h1:72tmFy5wsWx89uEVddd0RjRWPZm92WRLhf7AC+0+OOU=
github.com/go-openapi/loads v0.19.0/go.mod h1:72tmFy5wsWx89uEVddd0RjRWPZm92WRLhf7AC+0+OOU=
github.com/go-openapi/loads v0.19.2/go.mod h1:QAskZPMX5V0C2gvfkGZzJlINuP7Hx/4+ix5jWFxsNPs=

Used by FastAPI / Starlette:

* <a href="https://www.uvicorn.org" target="_blank"><code>uvicorn</code></a> - for the server that loads and serves your application.
* <a href="https://github.com/ijl/orjson" target="_blank"><code>orjson</code></a> - Required if you want to use `ORJSONResponse`.

Used by FastAPI / Starlette:

* <a href="https://www.uvicorn.org" target="_blank"><code>uvicorn</code></a> - for the server that loads and serves your application.
* <a href="https://github.com/ijl/orjson" target="_blank"><code>orjson</code></a> - Required if you want to use `ORJSONResponse`.

github.com/go-openapi/jsonreference v0.21.0/go.mod h1:LmZmgsrTkVg9LG4EaHeY8cBDslNPMo06cago5JNLkm4=
github.com/go-openapi/loads v0.22.0 h1:ECPGd4jX1U6NApCGG1We+uEozOAvXvJSF4nnwHZ8Aco=
github.com/go-openapi/loads v0.22.0/go.mod h1:yLsaTCS92mnSAZX5WWoxszLj0u+Ojl+Zs5Stn1oF+rs=
github.com/go-openapi/runtime v0.28.0 h1:gpPPmWSNGo214l6n8hzdXYhPuJcGtziTOgUpvsFWGIQ=

    The Apache projects are characterized by a collaborative, consensus based development process, an open and
    pragmatic software license, and a desire to create high quality software that leads the way in its field.
    We consider ourselves not simply a group of projects sharing a server, but rather a community of developers
    and users.
  </description>
  <licenses>
    <license>

As this component would take the **load** of requests and distribute that among the workers in a (hopefully) **balanced** way, it is also commonly called a **Load Balancer**.

!!! tip
    The same **TLS Termination Proxy** component used for HTTPS would probably also be a **Load Balancer**.

build:elinux_armhf --cpu=armhf
build:elinux_armhf --copt -mfp16-format=ieee

# Config-specific options should come above this line.

# Load rc file written by ./configure.
try-import %workspace%/.tf_configure.bazelrc
try-import %workspace%/xla_configure.bazelrc

# Load rc file with user-specific options.
try-import %workspace%/.bazelrc.user

# Here are bazelrc configs for release builds
# Build TensorFlow v2.

| `minio_system_cpu_avg_iowait` | `gauge` | Average CPU IOWait time            | `server` |
| `minio_system_cpu_load`       | `gauge` | CPU load average 1min              | `server` |
| `minio_system_cpu_load_perc`  | `gauge` | CPU load average 1min (percentage) | `server` |
| `minio_system_cpu_nice`       | `gauge` | CPU nice time                      | `server` |

from fastapi import FastAPI


def fake_answer_to_everything_ml_model(x: float):
    return x * 42


ml_models = {}


@asynccontextmanager
async def lifespan(app: FastAPI):
    # Load the ML model
    ml_models["answer_to_everything"] = fake_answer_to_everything_ml_model
    yield
    # Clean up the ML models and release the resources
    ml_models.clear()