Kellen Sunderland created MXNET-1084:
----------------------------------------
Summary: Enable FP16 Mode for Integrated TensorRT Inference
Key: MXNET-1084
URL: https://issues.apache.org/jira/browse/MXNET-1084
Project: Apache MXNet
Issue Type: Improvement
Reporter: Kellen Sunderland
As as an owner of a Turing, Volta, Pascal, or Jetson TX1 device, I would like
to run inference using TensorRT with FP16 DType tensors to make use of
dedicated hardware optimizations present.
Reference: https://devblogs.nvidia.com/tensor-core-ai-performance-milestones/
https://devblogs.nvidia.com/programming-tensor-cores-cuda-9/
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
