* **Machine Learning**: it normally requires lots of "matrix" and "vector" multiplications. Think of a huge spreadsheet with numbers and multiplying all of them together at the same time.

* **Machine Learning**: normalmente requiere muchas multiplicaciones de "matrices" y "vectores". Imagina en una enorme hoja de cálculo con números y tener que multiplicarlos todos al mismo tiempo.

Linux containers run using the same Linux kernel of the host (machine, virtual machine, cloud server, etc). This just means that they are very lightweight (compared to full virtual machines emulating an entire operating system).

This way, containers consume **little resources**, an amount comparable to running the processes directly (a virtual machine would consume much more).

Here's a little bit of that history.

## Alternatives

I have been creating APIs with complex requirements for several years (Machine Learning, distributed systems, asynchronous jobs, NoSQL databases, etc), leading several teams of developers.

As part of that, I needed to investigate, test and use many alternatives.

    * Le contenu est crypté, même s'il est envoyé avec le protocole HTTP.

Il est courant d'avoir un seul programme/serveur HTTP fonctionnant sur le serveur (la machine, l'hôte, etc.) et
gérant toutes les parties HTTPS : envoyer les requêtes HTTP décryptées à l'application HTTP réelle fonctionnant sur

## 服务器主机和服务器程序

关于名称，有一个小细节需要记住。 💡

“**服务器**”一词通常用于指远程/云计算机（物理机或虚拟机）以及在该计算机上运行的程序（例如 Uvicorn）。

请记住，当您一般读到“服务器”这个名词时，它可能指的是这两者之一。

当提到远程主机时，通常将其称为**服务器**，但也称为**机器**(machine)、**VM**（虚拟机）、**节点**。 这些都是指某种类型的远程计算机，通常运行 Linux，您可以在其中运行程序。


## 安装服务器程序

您可以使用以下命令安装 ASGI 兼容服务器：

=== "Uvicorn"

    * Die Inhalte sind **verschlüsselt**, auch wenn sie mit dem **HTTP-Protokoll** gesendet werden.

!!! tip "Consejo"
    Si lo estás dudando, "AlexNet", "ResNet", y "LeNet" son solo nombres de <abbr title="Técnicamente, arquitecturas de modelos de Deep Learning">modelos</abbr> de Machine Learning.

### Declara un *parámetro de path*

Luego, crea un *parámetro de path* con anotaciones de tipos usando la clase enum que creaste (`ModelName`):

```Python hl_lines="16"

{!../../../docs_src/advanced_middleware/tutorial002.py!}
```

The following arguments are supported:

* `allowed_hosts` - A list of domain names that should be allowed as hostnames. Wildcard domains such as `*.example.com` are supported for matching subdomains. To allow any hostname either use `allowed_hosts=["*"]` or omit the middleware.

If an incoming request does not validate correctly then a `400` response will be sent.

## `GZipMiddleware`

!!! tip "Dica"
	Se você está se perguntando, "AlexNet", "ResNet", e "LeNet" são apenas nomes de <abbr title="técnicamente, modelos de arquitetura de Deep Learning">modelos</abbr> de Machine Learning (aprendizado de máquina).

### Declare um *parâmetro de rota*

Logo, crie um *parâmetro de rota* com anotações de tipo usando a classe enum que você criou (`ModelName`):

```Python hl_lines="16"