Let's imagine that you have some **machine learning models** that you want to use to handle requests. 🤖

The same models are shared among requests, so, it's not one model per request, or one per user or something similar.

Let's imagine that loading the model can **take quite some time**, because it has to read a lot of **data from disk**. So you don't want to do it for every request.

				// Context is canceled, return at once.
				// request canceled, no entries to return
				return entries, io.EOF
			}
			if !IsErr(err, context.DeadlineExceeded, grid.ErrDisconnected) {
				// Report error once per bucket, but continue listing.x
				storageLogOnceIf(ctx, err, "GetMetacacheListing:"+o.Bucket)
			}
			o.Transient = true
			o.Create = false
			o.ID = mustGetUUID()
		} else {
			if c.fileNotFound {

If your lambda target expects an authorization token then you can enable it per function target as follows

```
MINIO_LAMBDA_WEBHOOK_ENABLE_function=on MINIO_LAMBDA_WEBHOOK_ENDPOINT_function=http://localhost:5000 MINIO_LAMBDA_WEBHOOK_AUTH_TOKEN="mytoken" minio server /data &
```

### Lambda Target with mTLS authentication

If your lambda target expects mTLS client you can enable it per function target as follows
```

| `minio_system_drive_reads_per_sec`             | Reads per second on a drive. <br><br>Type: gauge                                        | `drive`, `set_index`, `drive_index`, `pool_index`, `server`        |

			if orchestrated {
				return 30 * time.Second
			}
			return 10 * time.Minute
		}(),
		EnvVar: "MINIO_DNS_CACHE_TTL",
	},
	cli.IntFlag{
		Name:   "max-idle-conns-per-host",
		Usage:  "set a custom max idle connections per host value",
		Hidden: true,
		Value:  2048,
		EnvVar: "MINIO_MAX_IDLE_CONNS_PER_HOST",
	},
	cli.StringSliceFlag{
		Name:  "ftp",

        this.maxTotalConnections = maxTotalConnections;
    }

    /**
     * Sets the maximum connections per route.
     *
     * @param maxConnectionsPerRoute The maximum connections per route
     */
    public void setMaxConnectionsPerRoute(final Integer maxConnectionsPerRoute) {
        this.maxConnectionsPerRoute = maxConnectionsPerRoute;
    }

Build/Install - Performance - Support - Feature Request - Documentation Feature
Request - Documentation Bug - Others validations: required: true - type:
markdown attributes: value: | Please make sure that this is a bug. As per our
[GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md),we
only address code/doc bugs, performance issues, feature requests and
build/installation issues on GitHub.

-   type: markdown

type DiskInfoOptions struct {
	DiskID  string `msg:"id"`
	Metrics bool   `msg:"m"`
	NoOp    bool   `msg:"np"`
}

// DiskInfo is an extended type which returns current
// disk usage per path.
// The above means that any added/deleted fields are incompatible.
//
// The above means that any added/deleted fields are incompatible.
//
//msgp:tuple DiskInfo
type DiskInfo struct {
	Total      uint64

         * It has an added advantage since you can you easily switch to different hardware accelerators (cpu, gpu, tpu) as per the task.
         * All you need is a good internet connection and you are all set.
      * Try to build TF from sources by changing CPU optimization flags.
   
   *Please let us know if this helps.*
   
windows_comment: >

2. [Distributed Deployment](#distributed-deployment)
3. [Cloud Scale Deployment](#cloud-scale-deployment)

## 1. Standalone Deployment

To host multiple tenants on a single machine, run one MinIO Server per tenant with a dedicated HTTPS port, configuration, and data directory.

### 1.1 Host Multiple Tenants on a Single Drive

Use the following commands to host 3 tenants on a single drive:

```sh