-
Notifications
You must be signed in to change notification settings - Fork 46
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
OSPP: Cloud-edge collaborative inference for LLM based on KubeEdge-Ianvs #149
Conversation
ChangesIanvsCore
Denpendencies
Example
SednaSee details at FuryMartin/Sedna
|
CI will install sedna-0.4.1-py3-none-any.whl under However, since this PR updates Sedna, the old version installed in the CI environment lacks the new interfaces, leading to Run pylint '/home/runner/work/ianvs/ianvs/core'
************* Module core.testcasecontroller.algorithm.paradigm.base
core/testcasecontroller/algorithm/paradigm/base.py:130:19: E1123: Unexpected keyword argument 'cloud' in constructor call (unexpected-keyword-arg)
core/testcasecontroller/algorithm/paradigm/base.py:130:19: E1123: Unexpected keyword argument 'LCReporter_enable' in constructor call (unexpected-keyword-arg)
************* Module core.testenvmanager.dataset.dataset
core/testenvmanager/dataset/dataset.py:21:0: E0611: No name 'JsonlDataParse' in module 'sedna.datasources' (no-name-in-module)
core/testenvmanager/dataset/dataset.py:21:0: E0611: No name 'JSONDataInfoParse' in module 'sedna.datasources' (no-name-in-module)
-----------------------------------
Your code has been rated at 9.8/10
Error: The operation was canceled. It's a little tricky, I'm not sure how to solve it. I have written a detailed analysis of this issue in #134, and further discussions will take place there. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Reminder: there are CI issues that remain to be resolved, see https://github.com/kubeedge/ianvs/actions/runs/11201880744?pr=149
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The sedna installation originally used by the community should have a backup in third_party-bk.
520d514
to
5646e27
Compare
As discussed in #152 , this has been temporarily fixed by introducing
I have move the I have completed all the comment completion and document organization work. |
/lgtm |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
-
This branch has conflicts that must be resolved
Use the web editor or the to resolve conflicts.
Conflicting files
core/common/constant.py
core/testcasecontroller/algorithm/algorithm.py
core/testcasecontroller/algorithm/module/module.py
core/testcasecontroller/algorithm/paradigm/init.py
core/testcasecontroller/algorithm/paradigm/base.py
core/testenvmanager/dataset/dataset.py -
This pull request contains 12 commits, which might make maintenance difficult, considering the number of contributors, pull requests, and their commits in KubeEdge Ianvs recently. In the final stage, @FuryMartin can squash the commits into one using rebase techniques.
Thanks for the review. I'll fix them tomorrow. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Current conflicts:
This branch has conflicts that must be resolved
Use the web editor or the to resolve conflicts.
Conflicting files
core/common/constant.py
core/storymanager/rank/rank.py
core/testcasecontroller/algorithm/algorithm.py
core/testcasecontroller/algorithm/module/module.py
core/testcasecontroller/algorithm/paradigm/init.py
core/testcasecontroller/algorithm/paradigm/base.py
core/testcasecontroller/metrics/metrics.py
core/testenvmanager/dataset/dataset.py
Thanks for the review. These conflicts are caused by the revert #160.I believe they will be fixed automatically by merging #161 at first. Update at 2024-10-30 21:18#161 has been closed. @Yoda-wu is trying to create a new PR #162 contains the commits of #143 and #161. I advise @MooreZheng to first merge #162 , and then proceed with merging #144 . (Because I might have some conflicts with #144 as well) I will be on call any time tomorrow. Thanks! |
Sure. Will try following that path. |
/lgtm |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
After merging PR 162 and PR 144, the following new conflicts do come to fix
This branch has conflicts that must be resolved
Use the web editor or the to resolve conflicts.
Conflicting files
core/common/constant.py
core/testenvmanager/dataset/dataset.py
Fixed. |
3005581
to
0c6427c
Compare
Hi @MooreZheng , if possible, please merge #159 first, too. Reason#144 fix #152's pylint error by globally disable two style checks in dataset.py ianvs/core/testenvmanager/dataset/dataset.py Lines 20 to 21 in 27519de
As we discussed before, such global-disable-thing is not a good manner. #162, #144, #159 all used such method to pass the CI check. I have fixed it in my PR by including a new sedna package, so it's better to leave me the last to merge. BTW, #154 is not related to this issue, it can be merged at anytime. |
FYI I will on my flight tomorrow morning... Have talked to the #159 owner @safe-b on WeChat and left comments on his PR. @FuryMartin might want to lend him a hand to speed up the overall process. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Other OSPP projects have been merged, so this shall be the last conflict
This branch has conflicts that must be resolved
Use the web editor or the to resolve conflicts.
Conflicting files
core/testenvmanager/dataset/dataset.py
…example Signed-off-by: Yu Fan <[email protected]> add: sedna 0.6.0.1 and move 0.4.1 to third_party-bk Signed-off-by: Yu Fan <[email protected]>
Solved. |
/lgtm |
/approve |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
All concerns are fixed. Well done! @FuryMartin
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: MooreZheng The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
What type of PR is this?
/kind feature
What this PR does / why we need it:
Cloud-edge collaborative inference for LLM based on KubeEdge-Ianvs
Which issue(s) this PR fixes:
Fixes #96