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.

Sign up for GitHub

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

Jump to bottom

improved "capability" to judge operators migraphx can support #412

Open
scxiao opened this issue Dec 18, 2019 · 2 comments
Open

improved "capability" to judge operators migraphx can support #412

scxiao opened this issue Dec 18, 2019 · 2 comments
Assignees
@scxiao
Labels
onnxruntime PR changes interaction between MIGraphX and Onnxruntime

Comments

@scxiao
Copy link
Contributor

scxiao commented Dec 18, 2019

Current prototype to support onnxruntime uses a static analysis of operators that migraphx can or cannot support. But migraphx has the capability of inference some dynamic shapes for input graphs. This task is to use migraphx to analyze the operators that can or cannot be supported instead of the current static analysis, so better matches what migraphx is capable of doing.
@scxiao scxiao added the onnxruntime PR changes interaction between MIGraphX and Onnxruntime label Dec 18, 2019
@scxiao scxiao added this to the MIGraphX release 0.6 milestone Dec 18, 2019
@mvermeulen mvermeulen mentioned this issue Mar 11, 2020
Closed
@mvermeulen mvermeulen removed this from the MIGraphX release 0.7 milestone Jul 1, 2020
@nartmada
Copy link

Hi @scxiao, I am cleaning up old tickets here. If the task has been completed, please close the ticket. Thanks.

@ppanchad-amd
Copy link

Hi @mvermeulen, Has this task been completed? If so, please close the ticket. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@scxiao scxiao

Labels
onnxruntime PR changes interaction between MIGraphX and Onnxruntime
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@mvermeulen @scxiao @nartmada @ppanchad-amd