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

Add ModelCache e2e test #4136

Merged
merged 14 commits into from
Jan 11, 2025
Merged

Conversation

sivanantha321
Copy link
Member

@sivanantha321 sivanantha321 commented Dec 19, 2024

What this PR does / why we need it:

Which issue(s) this PR fixes (optional, in fixes #<issue number>(, fixes #<issue_number>, ...) format, will close the issue(s) when PR gets merged):
Fixes #3949

Type of changes
Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Feature/Issue validation/testing:

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

  • Test A

  • Test B

  • Logs

Special notes for your reviewer:

  1. Please confirm that if this PR changes any image versions, then that's the sole change this PR makes.

Checklist:

  • Have you added unit/e2e tests that prove your fix is effective or that this feature works?
  • Has code been commented, particularly in hard-to-understand areas?
  • Have you made corresponding changes to the documentation?

Release note:


Re-running failed tests

  • /rerun-all - rerun all failed workflows.
  • /rerun-workflow <workflow name> - rerun a specific failed workflow. Only one workflow name can be specified. Multiple /rerun-workflow commands are allowed per comment.

@sivanantha321 sivanantha321 force-pushed the modelcache-e2e-test branch 6 times, most recently from fe8e098 to 35bfe6f Compare December 20, 2024 12:44
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
Signed-off-by: Sivanantham Chinnaiyan <[email protected]>
@sivanantha321 sivanantha321 marked this pull request as ready for review January 7, 2025 03:28
@yuzisun
Copy link
Member

yuzisun commented Jan 11, 2025

/lgtm
/approve

@github-actions github-actions bot added the lgtm label Jan 11, 2025
@yuzisun yuzisun merged commit b7155b3 into kserve:master Jan 11, 2025
67 checks passed
gavrissh added a commit to gavrissh/kserve that referenced this pull request Jan 17, 2025
Signed-off-by: Gavrish Prabhu <[email protected]>

fix formatting

Signed-off-by: Gavrish Prabhu <[email protected]>

add vllm to poetry

Signed-off-by: Gavrish Prabhu <[email protected]>

Add affinity and tolerations to localmodel daemonset (kserve#4173)

* Add affinity and tolerations to localmodel daemonset

Signed-off-by: Jin Dong <[email protected]>

* make generate

Signed-off-by: Jin Dong <[email protected]>

---------

Signed-off-by: Jin Dong <[email protected]>

Fix s3 download PermanentRedirectError for legacy s3 endpoint (kserve#4157)

* sets virtual addressing style for legacy s3 endpoint

Signed-off-by: bentohset <[email protected]>

* add unit test

Signed-off-by: bentohset <[email protected]>

* fix formatting

Signed-off-by: bentohset <[email protected]>

* fix unit tests

Signed-off-by: bentohset <[email protected]>

---------

Signed-off-by: bentohset <[email protected]>
Co-authored-by: Lize Cai <[email protected]>

Make label and annotation propagation configurable (kserve#4030)

* Make label and annotation propagation configurable

chore:	Make the DisallaowedAnnotations and Labels configurable through
	ConfigMap so users can configured it quickly.

fixes kserve#3710

Signed-off-by: Spolti <[email protected]>

* generate boilerplate code

Signed-off-by: Spolti <[email protected]>

* Edgar's review changes

Signed-off-by: Spolti <[email protected]>

---------

Signed-off-by: Spolti <[email protected]>

Add ModelCache e2e test (kserve#4136)

* Add client sdk for localmodelcache, localmodelnodegroup

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Add e2e test for modelcache

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Use docker driver and minikube tunnel

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Merge "Allow multiple node groups in the model cache CR (kserve#4134)"

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Try mounting image dir

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Add local model agent to image scan

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Debug

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Create model root directory beforehand

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Restart kserve controller after patch

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Enablepvc direct mount in e2e test

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Reduce pv storage to 1GB

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Update modelcache test

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

* Update status-check to include modelcache logs

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

---------

Signed-off-by: Sivanantham Chinnaiyan <[email protected]>

Update vllm to 0.6.6 (kserve#4176)

Signed-off-by: Rajat Vig <[email protected]>
Co-authored-by: Dan Sun <[email protected]>

[bugfix] fix s3 storage download filename bug (kserve#4162)

* [bugfix] fix s3 storage download filename bug

- ensure correct path and file name preservation during s3 downloads in
  storage-initializer

Signed-off-by: Jaeyeon Kim <[email protected]>

* update lint

- fix format

Signed-off-by: Jaeyeon Kim <[email protected]>

* fix format

Signed-off-by: Jaeyeon Kim <[email protected]>

---------

Signed-off-by: Jaeyeon Kim <[email protected]>

update lint fix

Signed-off-by: Gavrish Prabhu <[email protected]>

update lint fix

Signed-off-by: Gavrish Prabhu <[email protected]>

update lint fix

Signed-off-by: Gavrish Prabhu <[email protected]>

openai model test

Signed-off-by: Gavrish Prabhu <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Add e2e test for local model cache
2 participants