mirror of https://github.com/llvm/torch-mlir
8486968925
With this + manually setting private visibility on everything, a simple classifier can be reduced to this IR, which is looking pretty lean and mean: https://gist.github.com/silvasean/19e7e2e21a61ff197aeac0dd864d188f Also, include a utility script for importing `.pt` models. ``` pt_util.py --import classifier.pt | npcomp-opt -torch-globalize-object-graph ``` |
||
---|---|---|
.. | ||
gen_aten_dialect.py | ||
pt_util.py |