Skip to content

chore: bump trtllm to v1.3.0rc23 - #12532

Merged
nv-anants merged 8 commits into
mainfrom
deps/upgrade-trtllm-v1.3.0rc23
Aug 5, 2026
Merged

chore: bump trtllm to v1.3.0rc23#12532
nv-anants merged 8 commits into
mainfrom
deps/upgrade-trtllm-v1.3.0rc23

Conversation

@dynamo-ops

@dynamo-ops dynamo-ops commented Aug 1, 2026

Copy link
Copy Markdown
Contributor

Automated dependency upgrade — trtllm v1.3.0rc23

Post-merge CI did not pass (conclusion: failure). Investigate before merging.

closes: OPS-8014

Summary by CodeRabbit

  • New Features
    • Updated the TensorRT-LLM integration to release 1.3.0rc23 across supported architectures.
  • Documentation
    • Refreshed compatibility tables, release metadata, and machine-readable release information.
  • Chores
    • Updated runtime image references, dependency pins, SBOM records, and associated integrity metadata.

Signed-off-by: dynamo-ops <170655669+dynamo-ops@users.noreply.github.com>
@dynamo-ops dynamo-ops added backend::trtllm Relates to the trtllm backend dep-upgrade Automated dependency upgrade labels Aug 1, 2026
@copy-pr-bot

copy-pr-bot Bot commented Aug 1, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@datadog-official

datadog-official Bot commented Aug 1, 2026

Copy link
Copy Markdown

Pipelines

⚠️ Warnings

🚦 2 Pipeline jobs failed

PR | backend-status-check   View in Datadog   GitHub Actions

PR | sglang-runtime / Test cuda13.0, amd64   View in Datadog   GitHub Actions

See error GPU memory limit exceeded while running tests, leading to execution failure.

Useful? React with 👍 / 👎

This comment will be updated automatically if new data arrives.
🔗 Commit SHA: c25db7c | Docs | Datadog PR Page | Give us feedback!

@github-actions github-actions Bot added chore documentation Improvements or additions to documentation container labels Aug 1, 2026
Re-captures the baseline SBOM against tensorrt-llm/release:1.3.0rc23
(digest release@316b840a) for both linux/amd64 and linux/arm64 and
updates context.yaml to the new stem.

Signed-off-by: Anant Sharma <anants@nvidia.com>
@nv-anants

Copy link
Copy Markdown
Member

/ok to test 2f7b61f

@github-actions

github-actions Bot commented Aug 4, 2026

Copy link
Copy Markdown
Contributor

Removes the rc22 manifest entries and SBOM files now that rc23 is the
tracked baseline.

Signed-off-by: Anant Sharma <anants@nvidia.com>
@nv-anants

Copy link
Copy Markdown
Member

/ok to test 9a74624

@nv-anants
nv-anants marked this pull request as ready for review August 4, 2026 16:47
@nv-anants
nv-anants requested review from a team as code owners August 4, 2026 16:47

@devin-ai-integration devin-ai-integration Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Devin Review found 1 potential issue.

Open in Devin Review

Comment thread pyproject.toml
@coderabbitai

coderabbitai Bot commented Aug 4, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

Walkthrough

The pull request updates TensorRT-LLM references from 1.3.0rc22 to 1.3.0rc23 across container metadata, SBOM records, the optional dependency, and release documentation.

Changes

TensorRT-LLM release alignment

Layer / File(s) Summary
Update release references
container/compliance/base_sboms/manifest.json, container/context.yaml, pyproject.toml, docs/fern/...
Runtime images, architecture-specific SBOM records, dependency metadata, and release documentation now reference 1.3.0rc23. The SBOM manifest includes updated digests, filenames, and generation timestamp.

Estimated code review effort: 2 (Simple) | ~10 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description explains the upgrade and CI failure but omits the required template sections and uses an invalid issue reference format. Add the Overview, Details, reviewer-start, and Related Issues sections, and use a valid issue reference such as Closes #XXXX or confirm that no issue is linked.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly and concisely identifies the TensorRT-LLM dependency upgrade to v1.3.0rc23.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.

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

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

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 current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@pyproject.toml`:
- Line 51: Constrain the `tensorrt-llm==1.3.0rc23` dependency in the `trtllm`
extra to the supported Python versions and platforms, or document the required
NVIDIA package index and supported targets for `ai-dynamo[trtllm]`; ensure
unsupported environments such as CPython 3.11 do not attempt to resolve it.
🪄 Autofix

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: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: c6512051-ea69-4527-a6d6-74506db0dcfe

📥 Commits

Reviewing files that changed from the base of the PR and between 7b099b1 and 9a74624.

📒 Files selected for processing (9)
  • container/compliance/base_sboms/manifest.json
  • container/compliance/base_sboms/release@316b840a-amd64.cdx.json
  • container/compliance/base_sboms/release@316b840a-arm64.cdx.json
  • container/context.yaml
  • docs/fern/assets/releases.json
  • docs/fern/components/releases.data.ts
  • docs/fern/pages/reference/general/compatibility.mdx
  • docs/fern/pages/reference/general/releases-machine-readable.mdx
  • pyproject.toml

Comment thread pyproject.toml
@nv-anants

Copy link
Copy Markdown
Member

/ok to test 446d086

@nv-anants
nv-anants enabled auto-merge (squash) August 5, 2026 14:51
Comment thread docs/fern/components/releases.data.ts Outdated
- Merge latest main (includes vllm-openai-xpu SBOM entry and other changes)
- Resolve manifest.json conflict: keep rc23 trtllm entries, drop rc22
- Add nixl[cu13]==1.3.1 to trtllm extra in pyproject.toml per review

Signed-off-by: Anant Sharma <anants@nvidia.com>
Previous merge commit re-sorted entries alphabetically as a side effect
of the conflict resolution script. This restores main's original ordering
so the diff against main only shows the rc22->rc23 swap.

Signed-off-by: Anant Sharma <anants@nvidia.com>
Addresses review comment from dagil-nvidia. Also reverts the incorrect
nixl[cu13] addition to pyproject.toml trtllm extra.

Signed-off-by: Anant Sharma <anants@nvidia.com>
@nv-anants

Copy link
Copy Markdown
Member

/ok to test c25db7c

@nv-anants
nv-anants merged commit 86fbcc0 into main Aug 5, 2026
186 of 188 checks passed
@nv-anants
nv-anants deleted the deps/upgrade-trtllm-v1.3.0rc23 branch August 5, 2026 20:51
hhzhang16 added a commit that referenced this pull request Aug 6, 2026
dyn-3691-extract-shared-target-pid-cuda-customstorage-operation-layer

* 'main' of https://github.com/ai-dynamo/dynamo: (65 commits)
  fix(frontend): emit SGLang stream role once (#12741)
  docs(fern): promote v1.3.1 to current release (#12752)
  fix(docs): remove duplicate unscoped community-rail CSS rules (#12615)
  feat(operator): migrate CRD storage to v1beta1 (#11904)
  fix: synchronize self-benchmark capacity across DP ranks (#12021)
  chore(deps): bump dynamo-tokenizers to 1.8.0 (#12707)
  fix(frontend): preserve split UTF-8 characters (#12688)
  docs: align Kubernetes build selector with CLI (#12729)
  fix(frontend): preserve completion backend error status (#12706)
  fix(operator): replace snapshot pods after GMS restart (#11286)
  refactor(media): rename installer module, drop --packages per review
  fix(media): harden installer against three pre-redesign review findings
  fix(media): verify installs in a fresh interpreter; teach --pip-args= form
  test(serve): install test-time decoders at the validated bounds
  feat(media): explicit installer for additional media decoders
  docs(spica): correct kv_load_ratio support guidance (#12714)
  feat(operator): add experimental grove.forceScalingGroup for single-node components (#11772)
  fix(vllm): declare entry-stage engine_input_source in GLM-Image NIXL config (#12709)
  chore: bump trtllm to v1.3.0rc23 (#12532)
  perf: remove trtllm postprocessing workers from the args as post processing workers are not effective in dynamo (#12592)
  ...

Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

backend::trtllm Relates to the trtllm backend chore container dep-upgrade Automated dependency upgrade documentation Improvements or additions to documentation size/XXL

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants