diff --git a/modules/chapter1/images/deploy_meaning.drawio.svg b/modules/chapter1/images/deploy_meaning.drawio.svg new file mode 100644 index 0000000..4d9ec7a --- /dev/null +++ b/modules/chapter1/images/deploy_meaning.drawio.svg @@ -0,0 +1,4 @@ + + + +
Applications that require to make inference
Applications th...
Runtime Server
Runtime Server
With a model
With a model
Data Science team
Data Science te...
Train and Deploy
Train and Deploy
Text is not SVG - cannot display
\ No newline at end of file diff --git a/modules/chapter1/images/draw.io/deploy_meaning.drawio b/modules/chapter1/images/draw.io/deploy_meaning.drawio new file mode 100644 index 0000000..9cb97dd --- /dev/null +++ b/modules/chapter1/images/draw.io/deploy_meaning.drawio @@ -0,0 +1 @@ +7VrbcuI4EP0aHkP5ivFjgLD7MFuTmkzVzOxLStjCViFbXlnmsl+/LVu+ikyYLJBJKlAFUuvSUp/TcrdgZM+T/R8cZfFfLMR0ZBnhfmQvRpZlOlMLvqTkUEk8364EESeh6tQKHsi/WAkNJS1IiPNeR8EYFSTrCwOWpjgQPRninO363daM9rVmKMKa4CFAVJd+I6GIK+nU8lr5n5hEca3ZnPhVywoFm4izIlX6UpbiqiVB9TRqj3mMQrbriOy7kT3njImqlOznmEqz1harxi2faG2WzHEqThkw+/z3Yfb503a7+eLcPE4JSyfxje9W02wRLZQt1GrFoTYOSUrrzVCeVbZfkz2GSWcZ5iTBAnOQgS4AC9+3olksEgotphxKSZRCOYC1lm2NMQyohCiP5YRlZc1SMWeU8VK57VieN5uBnKIVprPG3HWXEK9RQYUaqJhlWlJFhgKSRl9ZBhIbBGofC5JEYCVKVvBJVgl8FjnmOXyvJJMwH+fbCPory2Au8P5Jm5sNkuAcmMHe+QG61AMmyr61Xygu7FqSOUoUd/hVy5CiddRM3OILBQXxr8A9+YC7hbu4KNam/dpgex9gt2CHeEsCfEG4/deGe/oBt7VEWUZJgATYJK+qj0CAbePoa0JpZ03ytVyehxHWkBGmqzHCO8II72KM8J9nRL7BIogVYKwQlKR43kRZR1CE91KuYRZxFBLctpWhj2Zgw7ydThcSQ8HZBg869+gijQ/Q0U+SHvcsJxJEaFsxIVjS6XCrKCgkH3RCdsg6JFJZV5s3jvoBI3KWuy1MlqtJgOCZHJDsIxn9jtEud8Y5EDBBG8wfkzIaPguDbGvAoIl+pthHGGRfikGmYT5PIZyGtzIGlxhQlOck6INQOnmDMt4T8V21yPIPKR+7qrbYd7otDnUlhc1871Z+dCvtoLJWj6oWikMt9B/AAZthBQ/wCWGyQDzC4tlDWAe4A6B7BMBaxjGFo2vbX/AxVJWGe0nXzgnkDPhjDIhRbVSN6uYKw4n8/kTuYJ7KDto8JceaXf8f2lm/Fe1ujLHh2D3ujWXO+3P+lbXOU/TspJy8DVKa5yLldBhgu1dmpf1bsbJ3GJpXPAy9t8m7yUt551n9iVz/yrw74ZImKCDIDRsi/BIJa0KZ/RPOvSKl/DdBKXsY4b+UUs6Qm+ZpD1hAFR063cpwNX96wZqeifHTdWkbNHv9oVCt4Mz8/riVqi4oWCZz1oBR0MN4ydRHEGPKsgQWfb7LC2dq9HC2bD1VrWPJ3uXF4Il7xkRDv7247aXyhoiRKF34n4JwLAVsJK/ZN7JM0jWGzQdYIw4YSfR5cDQT7aatSqTxZZh/JiQMpZrZLiYCPwDUUucOkkTtjD0DZqYzwMzVk0P/usmhfr/wpUgF+B4IH8pbl/cLh+X1j8qp7kHXRaN+hHTQ+EZgKaBL+kn1m927RWOYG/ivDsfFbk7q8inJQh9OeR9Xvs4bvTUP8OfDN/81wzd34LLWi8O3wfWIee37EVPPRBdISD9/CEj1GDQERsn7dXjH9cYDNI/8AHNll9fztK8ckVQqS0P4XOCMssM7BsV0BqfwxSCBavvXicqv2r+m2Hf/AQ== \ No newline at end of file diff --git a/modules/chapter1/pages/index.adoc b/modules/chapter1/pages/index.adoc index 476fc0f..5182397 100644 --- a/modules/chapter1/pages/index.adoc +++ b/modules/chapter1/pages/index.adoc @@ -1,3 +1,19 @@ -= Chapter 1 += Model Serving in RHODS -This is the home page of _Chapter_ 1 in the *hello* quick course... \ No newline at end of file +In this chapter, we will describe the concepts and terminology around model serving on RHODS. + +Machine learning models must be deployed in a production environment to process real-time data and handle the problem they were designed to solve. + +Deploying a model in a production environment means that the model that has been trained, and exported to a model file format, needs to be imported in a runtime engine, and exposed for applications to consume. + +Consume from a model, means that software applications will use a communication method, often REST/HTTP to send a prompt request to a server, such server will fire a request to the model and provide a response. It is evident that the server processing the request, and providing a response based on the model needs to have access to such model. + +image::deploy_meaning.drawio.svg[] + +Here are some of the concepts that we will explain in this chapter: + +. Model Server +. Serving Runtime +. Model server authentication +. GPU Support for model serving +. Model serving formats \ No newline at end of file