"subnet": "10.1.0.0/16",
        "type": "host-local"
      },
      "type": "bridge"
    },
    {
      "sysctl": {
        "net.core.somaxconn": "500"
      },
      "type": "tuning"
    },
    {
      "ambient_enabled": false,
      "cni_agent_run_dir": "/path/to/kubeconfig",
      "dns": {},
      "exclude_namespaces": [
        ""
      ],
      "ipam": {},

        "subnet": "10.1.0.0/16",
        "type": "host-local"
      },
      "type": "bridge"
    },
    {
      "sysctl": {
        "net.core.somaxconn": "500"
      },
      "type": "tuning"
    },
    {
      "ambient_enabled": false,
      "cni_agent_run_dir": "/path/to/kubeconfig",
      "dns": {},
      "exclude_namespaces": [
        ""
      ],
      "ipam": {},

- `tuned`
- `curl`

### Install `tuned.conf` performance profile

#### Step 1 - download `tuned.conf` from the referenced link
```
wget https://raw.githubusercontent.com/minio/minio/master/docs/tuning/tuned.conf
```

#### Step 2 - install tuned.conf as supported performance profile on all nodes
```
sudo mkdir -p /usr/lib/tuned/minio/
sudo mv tuned.conf /usr/lib/tuned/minio
```

# areas may be consumed
vm.max_map_count=524288

# Default is 500000 = 0.5ms
kernel.sched_migration_cost_ns=5000000

# stalled hdd io threads
kernel.hung_task_timeout_secs=85

# network tuning for bigger throughput
net.core.netdev_max_backlog=250000
net.core.somaxconn=16384
net.ipv4.tcp_syncookies=0
net.ipv4.tcp_max_syn_backlog=16384
net.core.wmem_max=4194304
net.core.rmem_max=4194304

## <a href="https://github.com/tiangolo/uvicorn-gunicorn-fastapi-docker" class="external-link" target="_blank">tiangolo/uvicorn-gunicorn-fastapi</a>

Cette image est dotée d'un mécanisme d'"auto-tuning", de sorte qu'il vous suffit d'ajouter votre code pour obtenir automatiquement des performances très élevées. Et sans faire de sacrifices.

// token will receive heal status records from the running heal
// sequence.
//
// If no client token is provided, and a heal sequence is in progress
// an error is returned with information about the running heal
// sequence. However, if the force-start flag is provided, the server
// aborts the running heal sequence and starts a new one.

///

Dieses Image verfügt über einen **Auto-Tuning**-Mechanismus, um die **Anzahl der Arbeitsprozesse** basierend auf den verfügbaren CPU-Kernen festzulegen.

        replicas taking part in sync training.
    *   Performance improvements for GPU multi-worker distributed training using
        `tf.distribute.experimental.MultiWorkerMirroredStrategy`
    *   Update NVIDIA `NCCL` to `2.5.7-1` for better performance and performance
        tuning. Please see

The recommended way to handle the *startup* and *shutdown* is using the `lifespan` parameter of the `FastAPI` app as described above. If you provide a `lifespan` parameter, `startup` and `shutdown` event handlers will no longer be called. It's all `lifespan` or all events, not both.

You can probably skip this part.

///

There's an alternative way to define this logic to be executed during *startup* and during *shutdown*.

to the network can execute arbitrary code with the privileges of the user
running the `tf.train.Server`.

## Untrusted inputs during training and prediction

TensorFlow supports a wide range of input data formats. For example it can
process images, audio, videos, and text. There are several modules specialized
in taking those formats, modifying them, and/or converting them to intermediate