pip install -U "ray[train]"

import ray
from ray import train
from ray.train import ScalingConfig
from ray.train.torch import TorchTrainer
import torch
import torch.nn as nn

# Prepare for distributed (Ray handles device placement)
model = train.torch.prepare_model(model)

for epoch in range(10):
    # Your training loop
    output = model(torch.randn(32, 10))
    loss = output.sum()
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()

    # Report metrics (logged automatically)
    train.report({"loss": loss.item(), "epoch": epoch})

**That's it!** Ray handles:
- Distributed coordination
- GPU allocation
- Fault tolerance
- Checkpointing
- Metric aggregation

model = MyModel().cuda()
optimizer = torch.optim.Adam(model.parameters())

for epoch in range(epochs):
    for batch in dataloader:
        loss = model(batch)
        loss.backward()
        optimizer.step()

from ray.train.torch import TorchTrainer
from ray import train

def train_func(config):
    model = MyModel()
    optimizer = torch.optim.Adam(model.parameters())

    # Prepare for distributed (automatic device placement)
    model = train.torch.prepare_model(model)
    dataloader = train.torch.prepare_data_loader(dataloader)

    for epoch in range(epochs):
        for batch in dataloader:
            loss = model(batch)
            loss.backward()
            optimizer.step()

            # Report metrics
            train.report({"loss": loss.item()})

**Benefits**: Same code runs on 1 GPU or 1000 GPUs

from ray.train.huggingface import TransformersTrainer
from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments

def train_func(config):
    # Load model and tokenizer
    model = AutoModelForCausalLM.from_pretrained("gpt2")
    tokenizer = AutoTokenizer.from_pretrained("gpt2")

    # Training arguments (HuggingFace API)
    training_args = TrainingArguments(
        output_dir="./output",
        num_train_epochs=3,
        per_device_train_batch_size=8,
        learning_rate=2e-5,
    )

    # Ray automatically handles distributed training
    from transformers import Trainer
    trainer = Trainer(
        model=model,
        args=training_args,
        train_dataset=train_dataset,
    )

    trainer.train()

undefined

from ray import tune
from ray.train.torch import TorchTrainer
from ray.tune.schedulers import ASHAScheduler

def train_func(config):
    # Use hyperparameters from config
    lr = config["lr"]
    batch_size = config["batch_size"]

    model = MyModel()
    optimizer = torch.optim.Adam(model.parameters(), lr=lr)

    model = train.torch.prepare_model(model)

    for epoch in range(10):
        # Training loop
        loss = train_epoch(model, optimizer, batch_size)
        train.report({"loss": loss, "epoch": epoch})

**Result**: Distributed hyperparameter search across cluster

from ray import train
from ray.train import Checkpoint

def train_func(config):
    model = MyModel()
    optimizer = torch.optim.Adam(model.parameters())

    # Try to resume from checkpoint
    checkpoint = train.get_checkpoint()
    if checkpoint:
        with checkpoint.as_directory() as checkpoint_dir:
            state = torch.load(f"{checkpoint_dir}/model.pt")
            model.load_state_dict(state["model"])
            optimizer.load_state_dict(state["optimizer"])
            start_epoch = state["epoch"]
    else:
        start_epoch = 0

    model = train.torch.prepare_model(model)

    for epoch in range(start_epoch, 100):
        loss = train_epoch(model, optimizer)

        # Save checkpoint every 10 epochs
        if epoch % 10 == 0:
            checkpoint = Checkpoint.from_directory(
                train.get_context().get_trial_dir()
            )
            torch.save({
                "model": model.state_dict(),
                "optimizer": optimizer.state_dict(),
                "epoch": epoch
            }, checkpoint.path / "model.pt")

            train.report({"loss": loss}, checkpoint=checkpoint)

trainer = TorchTrainer(
    train_func,
    scaling_config=ScalingConfig(num_workers=8, use_gpu=True)
)

undefined

from ray.train import ScalingConfig

**Launch Ray cluster**:
```bash

undefined

ray status

If not connected:
```bash

**Issue: Out of memory**

Reduce workers or use gradient accumulation:
```python
scaling_config=ScalingConfig(
    num_workers=4,  # Reduce from 8
    use_gpu=True
)

if (i + 1) % accumulation_steps == 0:
    optimizer.step()
    optimizer.zero_grad()

**Issue: Slow training**

Check if data loading is bottleneck:
```python
import time

def train_func(config):
    for epoch in range(epochs):
        start = time.time()
        for batch in dataloader:
            data_time = time.time() - start
            # Train...
            start = time.time()
            print(f"Data loading: {data_time:.3f}s")

dataloader = DataLoader(dataset, num_workers=8)