Neuron runtime FAQs¶
Q: How does Neuron connect to all the Inferentia chips in an Inf1 instance?¶
By default, a single runtime process will manage all assigned Inferentias, including running the Neuron Core Pipeline mode. if needed, you can configure multiple KRT processes each managing a separate group of Inferentia chips. For more details please refer to Overview
Q: Where can I get logging and other telemetry information?¶
See this document on how to collect logs: Using Neuron GatherInfo Tool to collect debug and support information
Q: What about RedHat or other versions of Linux?¶
We dont officially support it yet.
Q: What about Windows?¶
Windows is not supported at this time.