TensorFlow Serving = the first mainstream model serving architecture in ML frameworks
+It serves ML models inside Google
+It is available in the cloud and via open-source
How it was created and how it works?
Thread⬇️
+It serves ML models inside Google
+It is available in the cloud and via open-source
How it was created and how it works?
Thread⬇️
Deep dive into "TensorFlow-Serving: Flexible, High-Performance ML Serving" by @JeremiahHarmsen, @FangweiLi, @sukritiramesh, Christopher Olston, Noah Fiedel, Kiril Gorovoy, Li Lao, Vinu Rajashekhar, Jordan Soyke
2/⬇️
2/⬇️
Paper outlined the architecture of a serving pipeline for @TensorFlow models
Capabilities of TensorFlow serving:
+model lifecycle management;
+experiments with multiple algorithms;
+efficient use of GPU resources
3/⬇️
Capabilities of TensorFlow serving:
+model lifecycle management;
+experiments with multiple algorithms;
+efficient use of GPU resources
3/⬇️
Fundamental building blocks of TensorFlow Serving:
+A C++ library consisting of APIs and modules from which to construct an ML server
+An assemblage of the library modules into a canonical server binary
+A hosted service
4/⬇️
+A C++ library consisting of APIs and modules from which to construct an ML server
+An assemblage of the library modules into a canonical server binary
+A hosted service
4/⬇️
The TensorFlow Serving paper was published together with the framework’s first implementation as part of the TensorFlow project.
Link: arxiv.org/abs/1712.06139
7/⬇️
Link: arxiv.org/abs/1712.06139
7/⬇️
TheSequence Edge covers:
+ML concept you should learn
+Review of an impactful research paper
+New ML framework or platform and how you can use it
thesequence.substack.com/p/-so-what-is-…
7/7
+ML concept you should learn
+Review of an impactful research paper
+New ML framework or platform and how you can use it
thesequence.substack.com/p/-so-what-is-…
7/7
• • •
Missing some Tweet in this thread? You can try to
force a refresh
