Skip to content

task(RHOAIENG-59028): Bump CUDA and ROCm images to Ray 2.54.1#797

Open
chipspeak wants to merge 1 commit intoopendatahub-io:mainfrom
chipspeak:RHOAIENG-59028
Open

task(RHOAIENG-59028): Bump CUDA and ROCm images to Ray 2.54.1#797
chipspeak wants to merge 1 commit intoopendatahub-io:mainfrom
chipspeak:RHOAIENG-59028

Conversation

@chipspeak
Copy link
Copy Markdown
Contributor

@chipspeak chipspeak commented Apr 23, 2026

Description

Bumped Ray version to 2.54.1 in both CUDA and ROCm runtime images.

How Has This Been Tested?

Merge criteria:

  • The commits are squashed in a cohesive manner and have meaningful messages.
  • Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious).
  • The developer has manually tested the changes and verified that the changes work

Summary by CodeRabbit

  • Chores
    • Updated Ray runtime to version 2.54.1 for CUDA (py312-cu128) and ROCm (py312-rocm64) variants
    • Updated build pipeline configurations to support Ray 2.54.1 releases

@openshift-ci
Copy link
Copy Markdown

openshift-ci Bot commented Apr 23, 2026

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign laurafitzgerald for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented Apr 23, 2026

Warning

Rate limit exceeded

@chipspeak has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 5 minutes and 45 seconds before requesting another review.

Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 5 minutes and 45 seconds.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Central YAML (base), Organization UI (inherited)

Review profile: CHILL

Plan: Pro Plus

Run ID: 67724336-37d3-414d-9dd6-e8edaf8f36da

📥 Commits

Reviewing files that changed from the base of the PR and between bf4b7b1 and 84553de.

⛔ Files ignored due to path filters (2)
  • images/runtime/ray/cuda/2.54.1-py312-cu128/Pipfile.lock is excluded by !**/*.lock
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/Pipfile.lock is excluded by !**/*.lock
📒 Files selected for processing (11)
  • .tekton/ray-2.54.1-py312-cu128-push.yaml
  • .tekton/ray-2.54.1-py312-rocm64-push.yaml
  • images/runtime/ray/cuda/2.54.1-py312-cu128/Dockerfile
  • images/runtime/ray/cuda/2.54.1-py312-cu128/NGC-DL-CONTAINER-LICENSE
  • images/runtime/ray/cuda/2.54.1-py312-cu128/Pipfile
  • images/runtime/ray/cuda/2.54.1-py312-cu128/README.md
  • images/runtime/ray/cuda/2.54.1-py312-cu128/cuda.repo-arm64
  • images/runtime/ray/cuda/2.54.1-py312-cu128/cuda.repo-x86_64
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/Dockerfile
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/Pipfile
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/README.md
📝 Walkthrough

Walkthrough

Six files are updated to increment Ray runtime version from 2.53.0 to 2.54.1 across CUDA and ROCm image variants. Changes include Tekton pipeline metadata names, path-change triggers, output-image parameters, and Pipfile/README version constraints. No behavioral logic modifications are present.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes


Security Assessment

No actionable security findings. Version bump alone does not introduce risk without examining upstream Ray 2.54.1 changelog for CVEs. Ensure dependency pinning with exact versions or SHAs if supply-chain risk is a concern—~=2.54.1 allows patch versions and may introduce unreviewed changes.

🚥 Pre-merge checks | ✅ 4
✅ Passed checks (4 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title directly and clearly summarizes the main change: bumping Ray versions from 2.53.0 to 2.54.1 for both CUDA and ROCm images.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Copy Markdown

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@images/runtime/ray/cuda/2.54.1-py312-cu128/Pipfile`:
- Line 8: Update the Pipfile dependency for "ray[all]" to pin the version
exactly: replace the version specifier "~=2.54.1" with "==2.54.1" in the line
that defines "ray[all]" so the Pipfile reflects an exact 2.54.1 pin (matches the
Pipfile.lock and prevents future 2.54.x drift).
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Central YAML (base), Organization UI (inherited)

Review profile: CHILL

Plan: Pro Plus

Run ID: 737b94de-ee6a-46b6-b578-8a9a8bf78bc7

📥 Commits

Reviewing files that changed from the base of the PR and between 564d2b3 and bf4b7b1.

⛔ Files ignored due to path filters (2)
  • images/runtime/ray/cuda/2.54.1-py312-cu128/Pipfile.lock is excluded by !**/*.lock
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/Pipfile.lock is excluded by !**/*.lock
📒 Files selected for processing (11)
  • .tekton/ray-2.54.1-py312-cu128-push.yaml
  • .tekton/ray-2.54.1-py312-rocm64-push.yaml
  • images/runtime/ray/cuda/2.54.1-py312-cu128/Dockerfile
  • images/runtime/ray/cuda/2.54.1-py312-cu128/NGC-DL-CONTAINER-LICENSE
  • images/runtime/ray/cuda/2.54.1-py312-cu128/Pipfile
  • images/runtime/ray/cuda/2.54.1-py312-cu128/README.md
  • images/runtime/ray/cuda/2.54.1-py312-cu128/cuda.repo-arm64
  • images/runtime/ray/cuda/2.54.1-py312-cu128/cuda.repo-x86_64
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/Dockerfile
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/Pipfile
  • images/runtime/ray/rocm/2.54.1-py312-rocm64/README.md

[packages]
numpy = {version = "<2.0.0" }
"ray[all]" = {version = "~=2.53.0" }
"ray[all]" = {version = "~=2.54.1" }
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Verify whether Ray runtime Pipfile.lock files pin Ray exactly for the new 2.54.1 images.
# Expected: either lockfiles exist and pin Ray to 2.54.1, or the Pipfile uses an exact ==2.54.1 pin.

set -u

echo "Pipfile constraints:"
rg -n '"ray\[all\]"\s*=\s*\{version\s*=\s*"(~=|==)2\.54\.1"' images/runtime/ray -C 1 || true

echo
echo "Pipfile.lock Ray entries, if present:"
fd '^Pipfile.lock$' images/runtime/ray | while read -r lockfile; do
  printf '\n== %s ==\n' "$lockfile"
  rg -n '"ray"|"ray\[all\]"|2\.54\.1' "$lockfile" -C 3 || true
done

Repository: opendatahub-io/distributed-workloads

Length of output: 2256


Pin ray[all] exactly in the 2.54.1 CUDA image Pipfile.

The Pipfile currently uses ~=2.54.1, which admits future 2.54.x releases under PEP 440. Although the committed Pipfile.lock pins Ray exactly to 2.54.1 and mitigates the immediate risk of silent version drift on rebuild, pinning exactly in the Pipfile itself follows supply-chain best practice (defense-in-depth) and closes the attack surface if the lockfile is ever bypassed or regenerated. Change to ==2.54.1.

Remediation diff
-"ray[all]" = {version = "~=2.54.1" }
+"ray[all]" = {version = "==2.54.1" }
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
"ray[all]" = {version = "~=2.54.1" }
"ray[all]" = {version = "==2.54.1" }
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@images/runtime/ray/cuda/2.54.1-py312-cu128/Pipfile` at line 8, Update the
Pipfile dependency for "ray[all]" to pin the version exactly: replace the
version specifier "~=2.54.1" with "==2.54.1" in the line that defines "ray[all]"
so the Pipfile reflects an exact 2.54.1 pin (matches the Pipfile.lock and
prevents future 2.54.x drift).

Signed-off-by: Pat O'Connor <paoconno@redhat.com>
@pawelpaszki
Copy link
Copy Markdown
Contributor

rocm part verified (details shared in slack)

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants