Skip to content

Conversation

@saturley-hall
Copy link
Member

@saturley-hall saturley-hall commented Sep 16, 2025

Overview:

Standardize the naming of your-registry and your-tag to my-registry and my-tag respectively for ease of scriptable replacement at release time.

Remove references to specific tags, in this case 0.4.1 and 0.5.0, in deference to my-tag

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

relates to OPS-1182

Summary by CodeRabbit

  • New Features

    • None.
  • Documentation

    • Updated deployment guides to use clearer example image references for sglang, TensorRT-LLM, and vLLM runtimes.
  • Chores

    • Refreshed default container image tags in deployment manifests to a new tag across vLLM and TensorRT-LLM components (Frontend, Decode/Prefill Workers, Planner, Prometheus).
    • Ensures deployments pull the updated runtime images; no config, resource, or behavior changes.

Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Sep 16, 2025

Walkthrough

Updated container image references across deployment YAMLs and READMEs for sglang, trtllm, and vllm backends. Tags were changed from specific or placeholder tags to “my-tag” and example registries updated to “my-registry”. No logic, configuration fields, or public APIs were altered.

Changes

Cohort / File(s) Summary of Changes
SGLang docs
components/backends/sglang/deploy/README.md
Example image updated from your-registry/sglang-runtime:your-tag to my-registry/sglang-runtime:my-tag.
TRTLLM docs + manifest
components/backends/trtllm/deploy/README.md, components/backends/trtllm/deploy/agg-with-config.yaml
README example image changed to my-registry/trtllm-runtime:my-tag. In YAML, two image refs updated from nvcr.io/.../tensorrtllm-runtime:0.4.1 to ...:my-tag (Frontend, TRTLLMWorker).
vLLM docs + manifests
components/backends/vllm/deploy/README.md, components/backends/vllm/deploy/agg.yaml, components/backends/vllm/deploy/agg_router.yaml, components/backends/vllm/deploy/disagg.yaml, components/backends/vllm/deploy/disagg_planner.yaml, components/backends/vllm/deploy/disagg_router.yaml
README example image changed to my-registry/vllm-runtime:my-tag. In YAMLs, image refs updated from nvcr.io/.../vllm-runtime:0.4.1 to ...:my-tag across Frontend, DecodeWorker, PrefillWorker, and Planner/Prometheus where present. No other fields changed.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

Poem

I nudge the tags from old to new,
Hop-hop through YAML dew.
Frontends, workers get their brew,
“my-tag” skies in a cleaner hue.
Carrots cached, images pull true—
Deploys now line up in a queue.
Thump! A merge; we’re through. 🥕

Pre-merge checks

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The PR description provides a clear Overview and a Related Issues line but does not follow the repository template: the required Details section describing specific changes and the "Where should the reviewer start?" section listing files to review are missing, and the referenced issue ID (OPS-1182) conflicts with the PR metadata (OPS-1167), leaving reviewers without file-level guidance or exact change details. Please update the description to include a Details section that lists the exact file changes and image/tag substitutions and add a "Where should the reviewer start?" section pointing to the key files (for example components/backends/{vllm,trtllm,sglang}/deploy/*.yaml and the modified README files), and correct the related issue ID to match the PR metadata.
✅ Passed checks (2 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
Title Check ✅ Passed The title succinctly and accurately summarizes the primary change—updating image tags for consistency and removing references to 0.4.1—and is concise, relevant, and directly reflects the YAML and README edits in this changeset.

Tip

👮 Agentic pre-merge checks are now available in preview!

Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.

  • Built-in checks – Quickly apply ready-made checks to enforce title conventions, require pull request descriptions that follow templates, validate linked issues for compliance, and more.
  • Custom agentic checks – Define your own rules using CodeRabbit’s advanced agentic capabilities to enforce organization-specific policies and workflows. For example, you can instruct CodeRabbit’s agent to verify that API documentation is updated whenever API schema files are modified in a PR. Note: Upto 5 custom checks are currently allowed during the preview period. Pricing for this feature will be announced in a few weeks.

Please see the documentation for more information.

Example:

reviews:
  pre_merge_checks:
    custom_checks:
      - name: "Undocumented Breaking Changes"
        mode: "warning"
        instructions: |
          Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).

Please share your feedback with us on this Discord post.


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
Contributor

@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

🧹 Nitpick comments (1)
components/backends/trtllm/deploy/README.md (1)

144-144: LGTM on my-registry/my-tag example.

Matches the convention introduced in this PR.

Small doc consistency nit: elsewhere in this README the sample image references nvcr.io/nvidian/... (note the “nvidian” spelling). Consider correcting to nvcr.io/nvidia/... and/or using the same placeholder style to avoid mixed examples.

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between fa6feee and 56dd552.

📒 Files selected for processing (9)
  • components/backends/sglang/deploy/README.md (1 hunks)
  • components/backends/trtllm/deploy/README.md (1 hunks)
  • components/backends/trtllm/deploy/agg-with-config.yaml (2 hunks)
  • components/backends/vllm/deploy/README.md (1 hunks)
  • components/backends/vllm/deploy/agg.yaml (2 hunks)
  • components/backends/vllm/deploy/agg_router.yaml (2 hunks)
  • components/backends/vllm/deploy/disagg.yaml (3 hunks)
  • components/backends/vllm/deploy/disagg_planner.yaml (5 hunks)
  • components/backends/vllm/deploy/disagg_router.yaml (3 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
  • GitHub Check: Build and Test - vllm
  • GitHub Check: Build and Test - dynamo
🔇 Additional comments (18)
components/backends/vllm/deploy/disagg_router.yaml (3)

16-16: Switched frontend image to my-tag — OK.

If release tooling replaces my-tag, confirm this file is included in that step.


30-30: Worker image tag standardized — OK.


47-47: Prefill worker image tag standardized — OK.

components/backends/vllm/deploy/agg.yaml (2)

16-16: Frontend image tag updated — looks good.


27-27: Decode worker image tag updated — looks good.

components/backends/vllm/deploy/agg_router.yaml (2)

16-16: Frontend image tag now uses my-tag — OK.


30-30: Decode worker image tag now uses my-tag — OK.

components/backends/vllm/deploy/disagg_planner.yaml (5)

23-23: Frontend image tag standardized — OK.


54-54: Planner image tag standardized — OK.


94-94: Prometheus image tag standardized — OK.


117-117: Decode worker image tag standardized — OK.


142-142: Prefill worker image tag standardized — OK.

Consider a follow-up to centralize the image tag (e.g., kustomize/helm values or CI substitution) to avoid drift across many files.

components/backends/vllm/deploy/disagg.yaml (2)

16-16: Frontend image tag updated — OK.


27-27: Decode worker image tag updated — OK.

components/backends/vllm/deploy/README.md (1)

119-119: Approve — placeholder standardized; verification required

LGTM; README now uses image: my-registry/vllm-runtime:my-tag and aligns with other backends.

Verification: the ripgrep run (rg -n "0.4.1|your-registry|your-tag" components/backends/vllm -S) returned no output in the provided execution, so absence of stragglers could not be confirmed. Re-run that command in the repository/CI and attach the output or confirm there are no matches.

components/backends/sglang/deploy/README.md (1)

95-95: LGTM for the README image change — update or confirm remaining sglang deploy image placeholders.

README change approved. Search shows these files still contain the placeholder image "my-registry/sglang-runtime:my-tag":

  • components/backends/sglang/deploy/agg.yaml
  • components/backends/sglang/deploy/agg_router.yaml
  • components/backends/sglang/deploy/agg_logging.yaml
  • components/backends/sglang/deploy/disagg.yaml
  • components/backends/sglang/deploy/disagg-multinode.yaml
  • components/backends/sglang/deploy/README.md

No occurrences of "your-registry"/"your-tag"/"0.4.1" were found under components/backends/sglang; note that repo‑wide "0.4.1" references still exist (e.g., pyproject.toml, docs, Cargo.lock) — confirm whether those version references should be updated.

components/backends/trtllm/deploy/agg-with-config.yaml (2)

37-37: LGTM: tag standardized consistently.

Both mainContainer image tags updated to my-tag as intended. No other manifest fields changed.

Also applies to: 53-53


37-37: Mark CI‑replaced image tag to avoid accidental deployments

Add an inline comment so the tag is obviously CI‑replaced in components/backends/trtllm/deploy/agg-with-config.yaml (also at the other occurrence). Apply this diff:

-          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:my-tag  # replaced by CI at release time

Verification: repository search returned many "0.4.1" release refs and several "your-" placeholders that should be audited. Notable matches: deploy/helm/chart/Chart.yaml, container/Dockerfile.trtllm, docs/_includes/install.rst, docs/_includes/quick_start_local.rst, benchmarks/nixl/README.md, deploy/inference-gateway/README.md, and multiple recipes//deploy.yaml files referencing vllm-runtime:0.4.1. Remove or replace any literal my-tag/your-tag in manifests used for deployment, or confirm they are intentionally instructional.

@saturley-hall saturley-hall requested a review from a team September 18, 2025 22:25
@saturley-hall saturley-hall enabled auto-merge (squash) September 19, 2025 20:07
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
@saturley-hall saturley-hall requested a review from a team as a code owner September 24, 2025 16:10
Copy link
Contributor

@nv-anants nv-anants left a comment

Choose a reason for hiding this comment

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

Copy link
Contributor

@nv-anants nv-anants left a comment

Choose a reason for hiding this comment

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

was working on something else and found a bunch under tests as well - https://github.com/ai-dynamo/dynamo/blob/main/tests/planner/scaling/disagg_planner.yaml#L119

@saturley-hall
Copy link
Member Author

was working on something else and found a bunch under tests as well - https://github.com/ai-dynamo/dynamo/blob/main/tests/planner/scaling/disagg_planner.yaml#L119

The tests are a more complicated place to change tag references (though in truth I have suspicions that these tests are not currently working). These look to point at the equivalent of my-registry/*-runtime:my-tag so maybe they are in scope here but I am more hesitant.

Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
@saturley-hall saturley-hall merged commit 9e8f67e into main Sep 24, 2025
16 of 18 checks passed
@saturley-hall saturley-hall deleted the harrison/ops-1167-update-the-container-tags-in-main branch September 24, 2025 18:53
jasonqinzhou pushed a commit that referenced this pull request Sep 24, 2025
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Jason Zhou <jasonzho@nvidia.com>
jasonqinzhou pushed a commit that referenced this pull request Sep 24, 2025
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Jason Zhou <jasonzho@nvidia.com>
jasonqinzhou pushed a commit that referenced this pull request Sep 24, 2025
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Jason Zhou <jasonzho@nvidia.com>
kylehh pushed a commit that referenced this pull request Sep 25, 2025
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
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.

3 participants