Re: [apache/tvm-rfcs] [RFC] Scalable Matrix Extension enablement (PR #107)

2024-03-12 Thread Tianqi Chen
I think it is helpful to add a discussion about how the flow would fit into the DLight usecases. I don't think it would likely cause too much of an overhead :) -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/107#issuecomment-1991996163 You are recei

Re: [apache/tvm-rfcs] [RFC] Scalable Matrix Extension enablement (PR #107)

2024-03-12 Thread Luke Hutton
Thanks @tqchen, at the moment the Relax flow would be out of scope for our current use-cases, although we'd want to make sure this RFC doesn't introduce obstacles for porting to the Relax flow in the future. Do you foresee any blockers with the current approach, or could we consider merging? --

Re: [apache/tvm-rfcs] [RFC] Scalable Matrix Extension enablement (PR #107)

2024-03-12 Thread Tianqi Chen
Thanks @lhutton1 , for relax and moving forward, one canonical example that can be helpful is the [https://github.com/apache/tvm/tree/main/python/tvm/dlight](dlight) package, which defines pattern matching and apply of transforms, that can then be used as part of pass. Right now dlight starte

Re: [apache/tvm-rfcs] [RFC] Scalable Matrix Extension enablement (PR #107)

2024-03-12 Thread Luke Hutton
Thanks for the discussion so far @tqchen, I added a small example detailing how we're registering schedules for the Relay flow. I believe this will have minimal impact for how the schedule might be used in a Relax based flow, but it would be good to hear your thoughts. -- Reply to this email d