refactor(examples) Update quickstart-pytorch to show how to run with …

…GPU (#4395)

Co-authored-by: jafermarq <[email protected]>

examples/quickstart-pytorch/README.md

@@ -48,7 +48,11 @@ You can run your Flower project in both _simulation_ and _deployment_ mode witho
 
 ### Run with the Simulation Engine
 
+> \[!TIP\]
+> This example might run faster when the `ClientApp`s have access to a GPU. If your system has one, you can make use of it by configuring the `backend.client-resources` component in `pyproject.toml`. If you want to try running the example with GPU right away, use the `local-simulation-gpu` federation as shown below.
+
 ```bash
+# Run with the default federation (CPU only)
 flwr run .
 ```
 
@@ -58,6 +62,13 @@ You can also override some of the settings for your `ClientApp` and `ServerApp`
 flwr run . --run-config "num-server-rounds=5 learning-rate=0.05"
 ```
 
+Run the project in the `local-simulation-gpu` federation that gives CPU and GPU resources to each `ClientApp`. By default, at most 5x`ClientApp` will run in parallel in the available GPU. You can tweak the degree of parallelism by adjusting the settings of this federation in the `pyproject.toml`.
+
+```bash
+# Run with the `local-simulation-gpu` federation
+flwr run . local-simulation-gpu
+```
+
 > \[!TIP\]
 > For a more detailed walk-through check our [quickstart PyTorch tutorial](https://flower.ai/docs/framework/tutorial-quickstart-pytorch.html)
 

examples/quickstart-pytorch/pyproject.toml

@@ -36,3 +36,8 @@ default = "local-simulation"
 
 [tool.flwr.federations.local-simulation]
 options.num-supernodes = 10
+
+[tool.flwr.federations.local-simulation-gpu]
+options.num-supernodes = 10
+options.backend.client-resources.num-cpus = 2 # each ClientApp assumes to use 2CPUs
+options.backend.client-resources.num-gpus = 0.2 # at most 5 ClientApp will run in a given GPU