Skip to content

[EP Perf] Fix on EP Perf - #20683

Merged
Yifan Li (yf711) merged 7 commits into
mainfrom
yifanl/ep_perf_sync_debug
May 16, 2024
Merged

[EP Perf] Fix on EP Perf#20683
Yifan Li (yf711) merged 7 commits into
mainfrom
yifanl/ep_perf_sync_debug

Conversation

@yf711

@yf711 Yifan Li (yf711) commented May 14, 2024

Copy link
Copy Markdown
Contributor

Description

  • Partially revert previous change, and
    • Redo concurrency_test_result parser outside of post.py
  • Add support of syncing memtest result to db

Motivation and Context

To fix the error when CI is running on two model groups.

  • When running on two model groups, the previous change wrongly navigates two levels up in the directory after running one model group, while one level is needed. After that, the script can't find another model group.
  • Running on one model group can't repro the issue

@yf711
Yifan Li (yf711) marked this pull request as ready for review May 14, 2024 23:28
@yf711
Yifan Li (yf711) requested a review from a team May 14, 2024 23:28
@yf711
Yifan Li (yf711) merged commit 47a178b into main May 16, 2024
@yf711
Yifan Li (yf711) deleted the yifanl/ep_perf_sync_debug branch May 16, 2024 04:38
@jywu-mysoft George Wu (jywu-mysoft) added the ep:TensorRT issues related to TensorRT execution provider label May 29, 2024
@sophies927 Sophie Schoenmeyer (sophies927) added the triage:approved Approved for cherrypicks for release label Jun 11, 2024
Yifan Li (yf711) added a commit that referenced this pull request Jun 21, 2024
### Description
<!-- Describe your changes. -->
* Partially revert [previous
change](#19804), and
   * Redo concurrency_test_result parser outside of post.py
* Add support of syncing memtest result to db


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
To fix the error when CI is running on two model groups.
- When running on two model groups, the [previous
change](#19804) wrongly
navigates two levels up in the directory after running one model group,
while one level is needed. After that, the script can't find another
model group.
- Running on one model group can't repro the issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ep:TensorRT issues related to TensorRT execution provider release:1.18.1 triage:approved Approved for cherrypicks for release

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants