Skip to content

Comments

Add the operation level execution use case#154

Merged
huningxin merged 3 commits intowebmachinelearning:masterfrom
huningxin:op_exec
Mar 30, 2021
Merged

Add the operation level execution use case#154
huningxin merged 3 commits intowebmachinelearning:masterfrom
huningxin:op_exec

Conversation

@huningxin
Copy link
Contributor

@huningxin huningxin commented Mar 20, 2021

Copy link
Member

@anssiko anssiko left a comment

Choose a reason for hiding this comment

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

With a typo fix.

Copy link
Collaborator

@pyu10055 pyu10055 left a comment

Choose a reason for hiding this comment

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

Do we want to limited the op execution to just CPU and GPU devices?
When ML accelerators are used in WebNN, are we recommending not to use op level execution?

@huningxin
Copy link
Contributor Author

huningxin commented Mar 23, 2021

@pyu10055 , thanks for your comments. Although some existing ML accelerators are designed to execute graph, I agree we should not limit the use case for that.

Added the "ML accelerator" in the new commit ac3f8a2. Please take another look.

@huningxin
Copy link
Contributor Author

Thanks for the review and approval!

@huningxin huningxin merged commit 880cd8a into webmachinelearning:master Mar 30, 2021
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