Closed PigletOS closed 5 months ago
Please refer to https://awsdocs-neuron.readthedocs-hosted.com/en/latest/frameworks/torch/torch-neuron/api-compilation-python-api.html - the minimum segment size to send to hardware during tracing is 2 by default. This prevents larger models getting badly fragmented.
If you want to trace a single operator please set this to 1: minimum_segment_size=1
Closing since this is expects + documented behavior.
Environment device : inf1.xlarge torch 1.3.1 torch-neuron 1.13.1.2.9.17.0
Problem I traced a single convolution layer and got this warning :
Log
Python Code test_conv_warning_cpu_trace.zip