Junru Shao
Junru Shao
My position: - Relay and Relax is going to co-exist as parallel submodules in TVM, and one should not affect the other at all; - Committed to keeping Relay source...
Thanks everyone for the year-long discussion. I'd love to note that, in respective, we would have already missed the boat of generative AI, and Apache TVM would have lost momentum...
Sure thing. I don’t think it’s an architectural decision though
CC: @sunggg
It’s up! https://twitter.com/bohanhou1998/status/1655772690760994818
Closed as it's complete. Please feel free to open up new issues for crashes or feature requests
Hey thanks for your interest! Our backend (TVM Unity) supports AMD CPUs out of box, so it wouldn’t be too challenging (likely tens of lines) to introduce support for them....
``` WARNING: lavapipe is not a conformant vulkan implementation, testing use only. ``` Seems that the Vulkan driver is not properly installed, because lavapipe is a CPU simulation of Vulkan
> The demo video also shows "WARNING: lavapipe is not a conformant vulkan implementation, testing use only.", so it might not be the issue. That's correct. `lavapipe` is a CPU-simulated...