Uh oh!
There was an error while loading. Please reload this page.
[TVM PyTorch Integration] libstdc++ CXX11 ABI Compatibility & boolean tensor support - #12232
Conversation
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
… tensor support (apache#12232) * first commit * rename * cmake * deprecated * newline * config * config * typo * skip tvm_class * rename * delete ptr * delete ptr * save progress * boolean support * cmake file * polish code * compile config * improving the codes * format * doc&errormsg * zero-cost copy * one step * to ndarray * extra output * delete extra codes * update test * boolean support * strong test * decrease memory copy * polish * reformat * polish * remove redundant import Co-authored-by: juda <yzhou@octoml.ai>
This PR solves two issues:
The compatibility of libstdc++ CXX11 ABI.
Currently, the official PyTorch distribution uses old symbols from libstdc++, which conflicts with the symbols used by TVM. The issue was discussed here before.
We address this issue by compiling the code snippets involving TVM and Torch separately, with their right libstdc++ CXX ABI. The TVM-related codes (RuntimeModuleWrapperTVM.cc) are built under the new CXX11 ABI, while the Torch-related codes (RuntimeModuleWrapperTorch.cc) are built under the same CXX11 ABI as the installed PyTorch, and linked together by a pure C header (runtime_bridge.h).
The lack of the support of boolean tensor.
Currently, If we tried to use
optimze_torchwith an input of boolean tensor, it will fail because it’s not supported by DLPack ([DISCUSS] Support kDLBool type dmlc/dlpack#75). We might want to work around it since some models use boolean tensor.We address this issue by extending the DLTensor with an extra
is_boolfield, guiding us to convert NDArray and DLTensor with the correct type. If the DLTensor is not boolean, the behavior of data transformation is the same as the previous codes.@yelite@masahi@junrushao1994