Uh oh!
There was an error while loading. Please reload this page.
[TVM] Add importer for ONNX QLinearMatMul op - #8952
Conversation
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
tmoreau89
commented
Sep 10, 2021
@cconvey may need to rebase and resolve conflicts given that test_forward has changed. @anwang2009 and @mbrookhart if you get cycles on Friday could you help review? thanks! |
6ec8769 to
277be0cCompareUh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
cconvey
commented
Oct 6, 2021
I just pushed a significantly revised version of the code, but it's not ready for review yet. |
Uh oh!
There was an error while loading. Please reload this page.
1092db4 to
d15bc48CompareUh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
5f8b0d4 to
23748c1Comparecconvey
commented
Oct 7, 2021
@mbrookhart@AndrewZhaoLuo ready for (re)review. |
| # express these constraints. | ||
| matmul_result_dtype = "int32" | ||
| matmul_result = _qnn.op.dense( |
There was a problem hiding this comment.
Can you add a TODO looking into refactoring this with regular MatMul code which handles broadcasting and the 3D cases already?
Feel free to assign it to you or me.
E.g.
TODO (AndrewZhaoLuo): ... or TODO(cconvey): ...
There was a problem hiding this comment.
I'm thinking that this should probably be part of a larger discussion about what collection of matmul-related ops are provided by Relay / Relax. If you don't mind I'll bring the topic up in a different forum.
There was a problem hiding this comment.
I mean the Matmul code in onnx, which handles numpy style broadcasting. That one is just a frontend change on how we generate relay from frontend code.
tmoreau89
commented
Oct 8, 2021
Also CC- @anwang2009 for the re-review |
e20764d to
ec16e22Comparembrookhart
commented
Oct 8, 2021
Looks like you hit #9231 |
* adds importer code * enables `test_qlinearmatmul_2D` unit test
ec16e22 to
484fd9dComparetmoreau89
commented
Oct 11, 2021
Thank you @cconvey@anwang2009@AndrewZhaoLuo@mbrookhart the PR has been merged! |
* adds importer code * enables `test_qlinearmatmul_2D` unit test
* adds importer code * enables `test_qlinearmatmul_2D` unit test
* adds importer code * enables `test_qlinearmatmul_2D` unit test
adds importer code
enables
test_qlinearmatmul_2Dunit test