Stateful actor: a parameter server¶
An actor keeps state between calls. One node creates the ParameterServer actor and a second node calls its set method.
When to use it. When workers must share mutable state, for example model weights, a cache or a counter, that would be lost between independent tasks.
The picture below is the graph drawn in Eugo's visual Ray builder, and the cell under Generated code is the Ray code the builder produced from it. The code is plain Ray: it runs without the builder.
Back to the gallery · Tested with Ray 2.55.1

The graph in Eugo's visual Ray builder.
Setup¶
Start a local Ray instance. The options keep the notebook quiet: no dashboard, and worker logs stay out of the notebook. Ray is capped at four CPUs so the example behaves the same on any machine. The generated code below only calls ray.init() when Ray is not running yet, so it reuses this instance.
import ray
ray.init(include_dashboard=False, log_to_driver=False, logging_level="ERROR", num_cpus=4)
RayContext(dashboard_url='', python_version='3.12.3', ray_version='2.55.1', ray_commit='237c2455ebb1ea15a32dd9e1fdeb2d617badc37f')
User functions¶
The nodes in the graph call these ordinary Python functions and classes. In the builder you write them in a normal notebook cell, and the generated code refers to them by name.
class ParameterServer:
# Leave the class undecorated: the generated code wraps it with ray.remote for you.
def __init__(self):
self.state = {}
def set(self, key, value):
self.state[key] = value
return value
def get(self, key):
return self.state.get(key)
Generated code¶
This is the cell the visual builder generated from the graph above.
# Generated with Eugo's visual Ray builder
import ray
if not ray.is_initialized():
ray.init()
ps = ray.remote(ParameterServer).remote()
_n2 = ps.set.remote("w", 42)
result = ray.get(_n2)
Check the result¶
The cell below checks that the generated code did what the graph describes.
assert result == 42, result
assert ray.get(ps.get.remote("w")) == 42
print("ps.get('w') =", ray.get(ps.get.remote("w")))
ps.get('w') = 42
How the graph maps to the code¶
Each step names a node in the picture, the lines of the generated cell it produced, and what those lines do. The node id (for example n1) is also the suffix of the variable that holds the node's result.
Setup (lines 1, 3 and 5–6)
# Generated with Eugo's visual Ray builder
...
import ray
...
if not ray.is_initialized():
ray.init()
The first line marks the cell as generated. The builder then adds an import for every Ray API the graph uses and a guarded ray.init(), so re-running the cell reuses the running cluster.
Actor (node n1, line 8)
ps = ray.remote(ParameterServer).remote()
Creates one actor process from the ParameterServer class. The handle ps is what other nodes use to call methods.
Actor method (node n2, lines 9–10)
_n2 = ps.set.remote("w", 42)
result = ray.get(_n2)
The method node is wired to the actor handle. ps.set.remote("w", 42) runs inside the actor, and ray.get returns the stored value.
Clean up¶
Shut down Ray, so the next notebook starts fresh.
ray.shutdown()