Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Relay][VM] Add ReshapeTensor instruction in the VM to replace the reshape op #6089

Merged
merged 5 commits into from
Jul 21, 2020

Conversation

icemelon
Copy link
Member

@jroesch @zhiics @mbrookhart Could you help review?

Copy link
Member

@zhiics zhiics left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@zhiics
Copy link
Member

zhiics commented Jul 18, 2020

Please check the error. We have gpu context in the check_result.

Copy link
Contributor

@mbrookhart mbrookhart left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@mbrookhart
Copy link
Contributor

The GPU error seems to come from the check I added to fail early on GPU with dynamic models. I believe dynamic shapes wont work on cuda until we get heterogenous execution working for shape funcs, per our discussion in https://discuss.tvm.ai/t/issue-with-vm-execution-when-testing-gpu-immediately-after-cpu/7010/7

@zhiics, any update on that work? Or should we limit this test to CPU?

@zhiics
Copy link
Member

zhiics commented Jul 18, 2020

@mbrookhart Yeah, I meant there is gpu context in the test. That's why the ci fails. We can probably just disable check_result for this test ATM. Heterogeneous execution needs this PR.

@zhiics zhiics merged commit 526b5a5 into apache:master Jul 21, 2020
@zhiics
Copy link
Member

zhiics commented Jul 21, 2020

Thanks @icemelon9 @mbrookhart

@icemelon icemelon deleted the vm-reshape branch July 21, 2020 21:33
@MarisaKirisame
Copy link
Contributor

@icemelon9 is_reshape_only is incorrect. If a function return a constant it will wrap a reshape on it. Please fix it in a principle way (e.g. not by checking that the whole function has at least one reshape, as this will not work on reshape of constant).

trevor-m pushed a commit to trevor-m/tvm that referenced this pull request Aug 26, 2020
…shape op (apache#6089)

* [VM] Add reshape tensor instruction

* update

* lint

* fix

* fix
trevor-m pushed a commit to trevor-m/tvm that referenced this pull request Aug 26, 2020
…shape op (apache#6089)

* [VM] Add reshape tensor instruction

* update

* lint

* fix

* fix
trevor-m pushed a commit to trevor-m/tvm that referenced this pull request Sep 2, 2020
…shape op (apache#6089)

* [VM] Add reshape tensor instruction

* update

* lint

* fix

* fix
trevor-m pushed a commit to neo-ai/tvm that referenced this pull request Sep 3, 2020
…shape op (apache#6089)

* [VM] Add reshape tensor instruction

* update

* lint

* fix

* fix
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants