Hello @huajsj I am super interested in your work!
As I have asked in [discussion
form](https://discuss.tvm.apache.org/t/can-tvm-split-work-into-different-layers-and-assign-layers-into-different-cores/11161?u=popojames),
I am using Hikey 970 with 4 big and 4 little CPUs to do inference now. One o
While working on unifying some device planning passes and cleaning up the
TECompiler we noticed we have a lot of issues around how we transition from
devices to Targets in the hetogeneous compilation flow. This pre-RFC is a stab
at fixing those. There's a somewhat larger issue around bringing BY
Thanks guys for the discussion! If the comments and concerns are all addressed,
let's move on and merge this PR after 24h
--
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/tvm-rfcs/pull/36#issuecommen
Merged #11 into main.
--
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/tvm-rfcs/pull/11#event-5375172043
Great discussions. If we are encouraging a common idiom(e.g. use T for tir).
We might actually want to encourage print in T as prefix to be consistent on
what users might write(and further edit with auto-completion), assuming we
always encourage user write `from tvm.script import tir as T`. As l
