Ray Serve: model multiplexing¶
One deployment serves many models: @serve.multiplexed loads a model by id on demand and keeps up to two per replica.
When to use it. Many small per-customer or per-language models that do not each justify a dedicated replica.
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.
Experimental. The builder lists a node in this graph in its Experimental section, so the node may change in later releases of the builder. The generated code ran on Ray 2.55.1.
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.
# The ModelRouter class is written by the builder from the node's settings.
from ray import serve
Generated code¶
This is the cell the visual builder generated from the graph above.
# Generated with Eugo's visual Ray builder
from ray import serve
import ray
if not ray.is_initialized():
ray.init()
@serve.deployment
class ModelRouter:
@serve.multiplexed(max_num_models_per_replica=2)
async def get_model(self, model_id: str):
return {"name": model_id}
async def __call__(self, request):
model_id = serve.get_multiplexed_model_id()
model = await self.get_model(model_id)
return model["name"]
_deploy_n1 = ModelRouter.bind()
serve.run(_deploy_n1)
DeploymentHandle(deployment='ModelRouter')
Check the result¶
The cell below checks that the generated code did what the graph describes. A Jupyter kernel already runs an asyncio event loop, so this cell awaits the Serve responses; in a plain Python script you would call .result() on them instead.
handle = serve.get_app_handle("default")
a = await handle.options(multiplexed_model_id="model-a").remote("ping")
b = await handle.options(multiplexed_model_id="model-b").remote("ping")
assert (a, b) == ("model-a", "model-b"), (a, b)
print("served by", a, "and", b)
served by model-a and model-b
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, 3–4 and 6–7)
# Generated with Eugo's visual Ray builder
...
from ray import serve
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.
Serve multiplexed (beta) (node n1, lines 9–18 and 20–21)
@serve.deployment
class ModelRouter:
@serve.multiplexed(max_num_models_per_replica=2)
async def get_model(self, model_id: str):
return {"name": model_id}
async def __call__(self, request):
model_id = serve.get_multiplexed_model_id()
model = await self.get_model(model_id)
return model["name"]
...
_deploy_n1 = ModelRouter.bind()
serve.run(_deploy_n1)
get_model is the loader decorated with @serve.multiplexed(max_num_models_per_replica=2); call reads the request's model id with serve.get_multiplexed_model_id() and awaits the cached model.
Clean up¶
Shut down Serve and then Ray, so the next notebook starts fresh.
from ray import serve
serve.shutdown()
ray.shutdown()