How to limited GPU memory? about simple_tensorflow_serving HOT 3 CLOSED

For the first question, we don't need the onnx python package because we use onnx_python which is already merged in mxnet python package. I think you can run all the ONNX without any other problem.

We can add the parameters such as per_process_gpu_memory_fraction to control the GPU devices soon.

from simple_tensorflow_serving.

@tobegit3hub Oh, Mybe I have something wrong, I will check it. I will look forward to new version with parameters of Controling the GPU device

from simple_tensorflow_serving.

It is supported now and you can use it with pip install -U simple_tensorflow_serving>=0.6.4.

More usage refers to https://github.com/tobegit3hub/simple_tensorflow_serving#gpu-acceleration .

from simple_tensorflow_serving.