I think fp32 makes sense, the problem is that NumPy defaults are arch. specific
and on 32-bit platforms the default sizing for both integers ("int") and
floating point ("float") are different. A problem that has plagued us
repeatedly. The behavior of `const` iirc is trying to normalize away the
platform specific behavior. In general I think its best to be a) consistent b)
opinionated.
---
[Visit
Topic](https://discuss.tvm.ai/t/discuss-the-meaning-of-float-in-relay/6949/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/c9b1d7907bc5a098b3113ef61c7e6c7be82b0f5ec15590bc02ae87760cabfe4c).
