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

add gpu monitor at web app #50

Merged

wejoncy merged 10 commits into microsoft:main from TITC:main

Oct 8, 2024

Contributor

TITC commented Oct 7, 2024

Thank you for taking the time to review this PR. Please handle it in the way you see fit. I would appreciate any suggestions to help me further improve my coding skills.

Video_20241007231737.mp4

TITC added 2 commits

October 7, 2024 15:28


          add gpu plot to the web app

eeda4c4


          revert model

c4a1822

Contributor Author

TITC commented Oct 7, 2024

@microsoft-github-policy-service agree

wejoncy reviewed

View reviewed changes

vptq/app_gpu.py Outdated Show resolved Hide resolved

wejoncy reviewed

View reviewed changes

vptq/app_gpu.py Outdated Show resolved Hide resolved


          amend fun doc in english

8deabc8

Contributor

wejoncy commented Oct 8, 2024

Thanks for your contribution on VPTQ project.

bash format would reslove the format issue.

LGTM.

wejoncy reviewed

View reviewed changes

models/Qwen2.5-7B-Instruct-v8-k65536-65536-woft Outdated Show resolved Hide resolved

TITC added 2 commits

October 8, 2024 06:48


          remove mis-commit file

0582e4e


          E501 and SIM117 problem

f0b3f9e

wejoncy reviewed

View reviewed changes

vptq/app.py Outdated Show resolved Hide resolved

TITC added 2 commits

October 8, 2024 08:09


          relative import-->module import

517d74e


          sort import

1fad204

wejoncy reviewed

View reviewed changes

vptq/app.py Outdated Show resolved Hide resolved

TITC added 3 commits

October 8, 2024 08:41


          revert moudle import

8bb171b


          yapf format

13cd3df


          yapf format

862933c

wejoncy merged commit d515ec5 into microsoft:main

7 checks passed

Contributor

YangWang92 commented Oct 8, 2024 •

edited

Loading

Hi @TITC @wejoncy Thanks for both of your help! You have done something I really wanted to do; now we can see the GPU utilization on the app interface, which will greatly help in demonstrating the memory overhead of our inference.

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

Labels

None yet