Skip to content

Multi-backend ML model inference server with TensorFlow, ONNX, and TVM support. Features performance benchmarking, concurrent inference, and model population management.

License

Notifications You must be signed in to change notification settings

luxu1986/ModelServer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

model_server

preparation

Prior to commencing the project build, kindly ensure that you follow the steps outlined in scirpt/prepare.sh to set up the compilation environment accordingly.

check

  • Enable bazel clean before build (which is disabled by default):
$ CLEAN=true ./build.sh
  • Disable static code check (which is enabled by default):
$ STATIC_CODE_CHECK=false ./build.sh
  • Enable unit-test and benchmark-test (which is disabled by default):
$ UNIT_TEST=true BENCHMARK_TEST=true ./build.sh

About

Multi-backend ML model inference server with TensorFlow, ONNX, and TVM support. Features performance benchmarking, concurrent inference, and model population management.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published