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

blogpost: boost quant perf #2

Closed
wants to merge 1 commit into from
Closed

Conversation

@jackwish
Copy link

jackwish commented Dec 29, 2019

The blogpost of quantization performance optimization from AliOS TVM team in Alibaba Group. We have planned this for a while. Would you mind to take a look at this @tqchen ?

I wrote the depthwise convolution optimization section on behalf of @FrozenGene. Please have a check and fix my misunderstandings if there were some @FrozenGene .

About the code sharing, as I am leaving the team, maybe @FrozenGene can help to track.

Also enable MathJax.
@jackwish

This comment has been minimized.

Copy link
Author

jackwish commented Jan 11, 2020

close due to inactive response.

@jackwish jackwish closed this Jan 11, 2020
@jackwish jackwish deleted the jackwish:quant branch Jan 11, 2020
@tqchen

This comment has been minimized.

Copy link
Member

tqchen commented Jan 11, 2020

Thanks @jackwish Sorry for not being active on this thread. I was hoping that we can merge the post after we have a code that folks can play with, so folks can have a clear reference to play with :)

@jackwish

This comment has been minimized.

Copy link
Author

jackwish commented Jan 11, 2020

Sure, I agree that ready-to-run code is very important as we declaring performance improvement. Unfortunately, I can not get it done as I have left the team.

Thank you.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
3 participants
You can’t perform that action at this time.