-
Notifications
You must be signed in to change notification settings - Fork 1.2k
Add ARM64 arch support for serving runtimes #3038
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
Conversation
2e04ec5
to
3cd4ee4
Compare
Thanks, the update looks straightforward to me. FWIW, I stumbled upon the same issue when cross-compiling (however, I "just" installed I wonder whether it would make sense to combine this with #3042 (if this makes sense to add), so that only one version bump would be required? |
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.
Thank you @sivanantha321 -- this is very helpful! The changes look good, but there is a lot of duplicated code in the workflow YAML files and the Dockerfiles.
For the GitHub actions/workflows, maybe we could Reusable Workflows or Composite Actions to wrap the boilerplate and just provide the Dockerfile and image name as parameters/inputs.
https://stackoverflow.com/a/71570847/5601796
Similarly, for the Dockerfiles, maybe create a(nother) common base image that contains all the common layers?
But since this PR is good as it is, those changes could go into a separate PR later. WDYT?
Thanks for the suggestion @ckadner. I agree with you. It would be nice to remove the duplicates. Let's handle it in a separate PR. |
@rhuss Thanks for the suggestion. But I think it is better to keep it as a different PR since, both are two different features. |
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.
/lgtm
Need to resolve merge conflicts still, though.
Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
3cd4ee4
to
f71f786
Compare
@yuzisun @ckadner Currently, Paddle does not have support for ARM64. |
I think that's okay. We could keep track of that in a separate issue. |
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.
/lgtm
/approve
[APPROVALNOTIFIER] This PR is APPROVED Approval requirements bypassed by manually added approval. This pull-request has been approved by: ckadner, sivanantha321 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 |
Except for Paddle, which does not support arm64/aarch64 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
Except for Paddle, which does not support arm64/aarch64 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: Jin Dong <jdong183@bloomberg.net>
* Fix configmap docs removed by kustomize build (#3024) Signed-off-b 8000 y: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Loosen ray version range (#2993) * Loosen ray range Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> * Fix import of RayServeHandle ref ray-project/ray#34714 Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> * Allow pandas 2.0 Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> * Remove exclusion markers Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> * Run poetry lock --no-update Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> --------- Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> * Retry on resource conflict error (#3035) Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * chore: Fix `no space left on device` error in `predictor-runtime-build` (#3049) * Create a separate action to free-up disk space on GH action runner * Move 'free-up-disk-space' step outside 'minikube-setup' action * Free-up disk space before running 'predictor-runtime-build' Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * Update MM version to v0.11.0-rc1 (#3047) Signed-off-by: Rafael Vasquez <raf.vasquez@ibm.com> * Bump scikit-learn version to 1.3.0 (#3040) * Bump scikit-learn version to 1.3.0 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Update test models Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Downgrade ray serve to 2.4 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * template out kube-rbac-proxy image (#3048) * template out kube-rbac-proxy image Signed-off-by: Tessa Pham <hpham111@bloomberg.net> * add kserve-addressable-resolver to clusterroles Signed-off-by: Tessa Pham <hpham111@bloomberg.net> --------- Signed-off-by: Tessa Pham <hpham111@bloomberg.net> * Add ARM64 arch support for serving runtimes (#3038) Except for Paddle, which does not support arm64/aarch64 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Support secret name overrides with annotation (#3034) * Add annotation for secret name overrides Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Remove the field Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix secret name annotation Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update kserve url storage example docs Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Address review comments Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update config docs for storage secret Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix storage secret name Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Add test for secret name annotation override Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix flake8 lint Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Dan Sun <dsun20@bloomberg.net> * release: Update defaultModelMeshVersion to v0.11.0 (#3059) Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * chore: Rename ModelMesh validating webhook (#3064) Resolves #3063 Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * Release v0.11.0 (#3061) Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Update poetry lock files (#3066) Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: ddelange <14880945+ddelange@users.noreply.github.com> Signed-off-by: Christian Kadner <ckadner@us.ibm.com> Signed-off-by: Rafael Vasquez <raf.vasquez@ibm.com> Signed-off-by: Tessa Pham <hpham111@bloomberg.net> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> Co-authored-by: Sivanantham <90966311+sivanantha321@users.noreply.github.com> Co-authored-by: ddelange <14880945+ddelange@users.noreply.github.com> Co-authored-by: Christian Kadner <ckadner@us.ibm.com> Co-authored-by: Rafael Vasquez <raf.vasquez@ibm.com> Co-authored-by: Tessa Pham <hpham111@bloomberg.net> Co-authored-by: Andrews Arokiam <87992092+andyi2it@users.noreply.github.com>
Except for Paddle, which does not support arm64/aarch64 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: Jin Dong <jdong183@bloomberg.net>
Except for Paddle, which does not support arm64/aarch64 Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: iamlovingit <freecode666@gmail.com>
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 #2989
Type of changes
Please delete options that are not relevant.
Feature/Issue validation/testing:
Please describe the tests that you ran to verify your changes and relevent 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:
Checklist:
Release note: