[None][doc] Update the image links in tech blog 19/20/21.

[nv-guomingz]

Summary by CodeRabbit

• Documentation
  • Updated images in three technical blog posts for improved accessibility: "Distributed Weight Data Parallelism for High Performance LLM Inference on NVL72," "Tuning CUDA Graph Batch Sizes for Higher Output Throughput," and "Temporal Correlation Meets Sparse Attention."
  • Updated author attribution in one blog post.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[nv-guomingz]

/bot run

[coderabbitai]

📝 Walkthrough

Walkthrough

This pull request updates three technical blog posts to host embedded figures on GitHub raw content URLs instead of relative local paths. Blog19 updates four figures, blog20 updates three figures and the author credit line, and blog21 updates ten figures throughout. All changes maintain document structure and content—only image source references change.

Changes

Blog Image URL Migration

Layer / File(s)

Summary

Image URL Migration docs/source/blogs/tech_blog/blog19_DWDP_...md, docs/source/blogs/tech_blog/blog20_Tuning_CUDA_...md, docs/source/blogs/tech_blog/blog21_Temporal_Correlation_...md

Four figures in blog19 (Motivation, DWDP Overview, DWDP runtime flow, async communication contention) are migrated to GitHub raw URLs. Blog20 author text is updated to "NVIDIA TensorRT LLM Team" and three figures (Figure 1, 2, 3) are migrated. Blog21 ten figures (indexer Top-K, Top-K hit ratio, temporal correlation, GVR algorithm, secant threshold, Phase 4 refinement, dispatch logic, synthetic scaling, per-layer latency, end-to-end TPOT reduction) are migrated to GitHub raw URLs.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is largely empty, containing only the template with no actual content filled in for the key sections.	Complete the Description and Test Coverage sections. Explain what images were changed, why the links were updated, and identify any tests relevant to documentation changes.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: updating image links in tech blogs 19, 20, and 21, with proper format including ticket type [None][doc].
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.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[coderabbitai]

Actionable comments posted: 1

🧹 Nitpick comments (1)

docs/source/blogs/tech_blog/blog20_Tuning_CUDA_Graph_Batch_Sizes_for_Higher_Output_Throughput.md (1)

64-64: ⚡ Quick win

Prefer commit-pinned raw image URLs for long-term doc stability.

These links target raw/main, so future file moves/renames on main can break historical blog rendering. Consider pinning to a commit SHA (or a docs-hosted asset path) for immutable references.

Also applies to: 77-77, 118-118

🤖 Prompt for 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.

In
`@docs/source/blogs/tech_blog/blog20_Tuning_CUDA_Graph_Batch_Sizes_for_Higher_Output_Throughput.md`
at line 64, The image URL uses the volatile raw/main path; update the img src
for the image named tech_blog20_aggr_all_models.png to a commit-pinned raw URL
(replace raw/main with the specific commit SHA raw URL) or switch to a stable
docs-hosted asset path, keeping the same alt and width attributes; apply the
same change for the other blog image src occurrences mentioned (the two other
image references in this file) so all image links are immutable.

🤖 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
`@docs/source/blogs/tech_blog/blog20_Tuning_CUDA_Graph_Batch_Sizes_for_Higher_Output_Throughput.md`:
- Line 3: Replace the inconsistent author string "By NVIDIA TensorRT LLM Team"
with the normalized branding used elsewhere ("By TensorRT-LLM") in the blog
front-matter/header so it matches other updated posts; locate the author line
containing "By NVIDIA TensorRT LLM Team" and update it to "By TensorRT-LLM".

---

Nitpick comments:
In
`@docs/source/blogs/tech_blog/blog20_Tuning_CUDA_Graph_Batch_Sizes_for_Higher_Output_Throughput.md`:
- Line 64: The image URL uses the volatile raw/main path; update the img src for
the image named tech_blog20_aggr_all_models.png to a commit-pinned raw URL
(replace raw/main with the specific commit SHA raw URL) or switch to a stable
docs-hosted asset path, keeping the same alt and width attributes; apply the
same change for the other blog image src occurrences mentioned (the two other
image references in this file) so all image links are immutable.

🪄 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: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: ab5f95c0-192f-4691-9504-e3363fe30fa9

📥 Commits

Reviewing files that changed from the base of the PR and between 16da4e9 and 71c8ef0.

📒 Files selected for processing (3)

• docs/source/blogs/tech_blog/blog19_DWDP_Distributed_Weight_Data_Parallelism_for_High_Performance_LLM_Inference_on_NVL72.md
• docs/source/blogs/tech_blog/blog20_Tuning_CUDA_Graph_Batch_Sizes_for_Higher_Output_Throughput.md
• docs/source/blogs/tech_blog/blog21_Temporal_Correlation_Meets_Sparse_Attention.md

[tensorrt-cicd]

PR_Github #47136 [ run ] triggered by Bot. Commit: 71c8ef0 Link to invocation

[tensorrt-cicd]

PR_Github #47136 [ run ] completed with state SUCCESS. Commit: 71c8ef0
/LLM/main/L0_MergeRequest_PR pipeline #37100 completed with status: 'SUCCESS'

CI Report

Link to invocation