mirror of
https://github.com/vale981/ray
synced 2025-03-12 06:06:39 -04:00
d809d748cf
This change adds introductory deployment graph documentation. Links to updated documentation: * [Model Composition](https://ray--26860.org.readthedocs.build/en/26860/serve/model_composition.html) * [Examples Overview](https://ray--26860.org.readthedocs.build/en/26860/serve/tutorials/index.html) * [Deployment Graph Pattern Overview](https://ray--26860.org.readthedocs.build/en/26860/serve/tutorials/deployment-graph-patterns.html) * [Pattern: Linear Pipeline](https://ray--26860.org.readthedocs.build/en/26860/serve/tutorials/deployment-graph-patterns/linear_pipeline.html) * [Pattern: Branching Input](https://ray--26860.org.readthedocs.build/en/26860/serve/tutorials/deployment-graph-patterns/branching_input.html) * [Pattern: Conditional](https://ray--26860.org.readthedocs.build/en/26860/serve/tutorials/deployment-graph-patterns/conditional.html) Co-authored-by: Archit Kulkarni <architkulkarni@users.noreply.github.com>
1.1 KiB
1.1 KiB
(deployment-graph-pattern-branching-input)=
Pattern: Branching Input
This deployment graph pattern lets you pass the same input to multiple deployments in parallel. You can then aggregate these deployments' intermediate outputs in another deployment.
Code
:language: python
:start-after: __graph_start__
:end-before: __graph_end__
Execution
This graph includes two Model nodes, with weights of 0 and 1. It passes the input into the two Models, and they add their own weights to it. Then, it uses the combine deployment to add the two Model deployments' outputs together.
The resulting calculation is:
input = 1
output1 = input + weight_1 = 0 + 1 = 1
output2 = input + weight_2 = 1 + 1 = 2
combine_output = output1 + output2 = 1 + 2 = 3
The final output is 3:
$ python branching_input.py
3