Closed #2030.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/2030#event-2952622758
close this for now.
The new Unified IR RFC #4617 covers this aspect, by using relay's Op as a
single source to register the related information.
The follow up refactors will be able to reflect that
--
You are receiving this because you are subscribed to this thread.
Reply to this email direc
Please join us to welcome @FrozenGene as a new committer
He as been an active advocator of TVM. He has helped reviewed many code related
to backend codegen and TFLite support. He also contributed to various areas of
the codebase including C++ RPC, Arm support and LLVM related code. He recently
Hi Henry,
Thanks for asking the question. It depends on how and to what extent
AWS is gonna release its low level API. To put on my Amazon hat (and I
work closely with inferentia team), this is still not clear. We need
more time to investigate.
It is definitely feasible If we only treat TVM as a
Hi All,
I remember someone asked about AWS Neuron SDK [1] during TVM summit.
AFAIK it is used to support AWS new Inferentia chip that focus for low
power and low precision inferences jobs.
Does anyone have followup whether would make sense to add support in TVM
for the new AWS Inferentia chip [2]
