@comaniac @matt-arm @masahi
Sorry for the delay! The Meetup this morning ate more of my time than I
expected.
https://github.com/apache/incubator-tvm/pull/5646
---
[Visit
Topic](https://discuss.tvm.ai/t/byoc-use-pattern-language-to-create-composite-functions/6727/28)
to respond.
You
Hi There,
VTA first conv layer is running on CPU and not get offload into FPGA, in most
case that is a performance bottle neck and need optimization, following are
some idea about the
optimization, please kindly comments.
Regards
Hua
1. training network to make first conv layer support int8
Thanks to @tqchen, @mbrookhart, and @matt-arm for the great talks and ~40 for
attending for a great first Online TVM Meetup!
Video is now up on Youtube [here](https://youtu.be/U_j1Yc-6sxM). And the agenda
is
[here](https://docs.google.com/document/d/1bfE7Ydk43aMM3aiLf8GM7xEatPJwhj839ANfBheUJc
Updated the gist with merged features (configurable partition function
attributes; pattern with more powerful attributes).
Once the last feature (partition callback) is in, we should be fine to rewrite
`MergeComposite` pass without any loss.
https://gist.github.com/comaniac/1f399dfdfee05a2f7a