Yep, also curious about the followup. Is the Hexagon backend fully supported
now? Or SNPE is still the only toolchain we can use to compile models to
Qualcomm GPU.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/introducing-hexagon-backend/2421/35) to
respond.
You are receiving this
It is supported in the sense that you should be able to compile and execute any
model. There is still a lot of work we need to do to make it perform well.
Right now we're working on many infrastructural changes in TVM, and the actual
code generated for Hexagon is still far from optimal.
