[None][doc] Update tech blog12 #7884
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
/bot skip --comment "doc changes only" |
📝 WalkthroughWalkthroughEdits to a single documentation blog post update image widths, add explicit external references and PR links, and refine wording around CUDA/GIL topics and bindings. No code, APIs, or data structures changed. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches🧪 Generate unit tests
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.
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
docs/source/blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.md (2)
3-3: Fix byline formatting to satisfy MD036 (no-emphasis-as-heading).Avoid an emphasis-only line. Make it plain text to appease markdownlint.
Apply this diff:
-*By NVIDIA TensorRT LLM Team and the XGrammar Team* +By NVIDIA TensorRT LLM Team and the XGrammar Team
52-52: Add meaningful alt text to all images (MD045).Improves accessibility and passes markdownlint.
Apply this diff:
- <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_constrained_decoding_pipeline_overlap.png" width="800"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_constrained_decoding_pipeline_overlap.png" alt="Guided decoding timeline with and without overlapping" width="800"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_one_model_vs_two_model.png" width="800"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_one_model_vs_two_model.png" alt="GPU timeline of one-model vs two-model speculative decoding" width="800"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_cpu_gpu_synchronization_for_multiple_steps.png" width="1000"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_cpu_gpu_synchronization_for_multiple_steps.png" alt="CPU–GPU synchronization across multiple steps" width="1000"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_cpu_gpu_synchronization_for_multiple_steps_by_cuda_callback.png" width="1000"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_cpu_gpu_synchronization_for_multiple_steps_by_cuda_callback.png" alt="CPU–GPU synchronization via CUDA callbacks across multiple steps" width="1000"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_mode_eval_llama_3.1_8b.png" width="800"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_mode_eval_llama_3.1_8b.png" alt="Pareto curve on JSON Mode Eval for LLaMA 3.1 8B" width="800"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_mode_eval_llama_3.3_70b.png" width="800"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_mode_eval_llama_3.3_70b.png" alt="Pareto curve on JSON Mode Eval for LLaMA 3.3 70B" width="800"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_schema_bench_llama_3.1_8b.png" width="800"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_schema_bench_llama_3.1_8b.png" alt="Pareto curve on JSON Schema Bench for LLaMA 3.1 8B" width="800"> - <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_schema_bench_llama_3.3_70b.png" width="800"> + <img src="https://github.com/NVIDIA/TensorRT-LLM/raw/main/docs/source/blogs/media/tech_blog12_pareto_curve_json_schema_bench_llama_3.3_70b.png" alt="Pareto curve on JSON Schema Bench for LLaMA 3.3 70B" width="800">Also applies to: 65-65, 86-86, 142-142, 264-264, 272-272, 283-283, 290-290
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.md(8 hunks)
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-08-20T07:43:36.447Z
Learnt from: ChristinaZ
PR: NVIDIA/TensorRT-LLM#7068
File: cpp/tensorrt_llm/kernels/moeTopKFuncs.cuh:169-172
Timestamp: 2025-08-20T07:43:36.447Z
Learning: In TensorRT-LLM MOE kernels, when processing up to 128 experts across 32 threads, each thread handles at most 4 experts (N < 5 constraint), where N represents candidates per thread rather than total system capacity.
Applied to files:
docs/source/blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.md
🪛 markdownlint-cli2 (0.18.1)
docs/source/blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.md
3-3: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
52-52: Images should have alternate text (alt text)
(MD045, no-alt-text)
65-65: Images should have alternate text (alt text)
(MD045, no-alt-text)
86-86: Images should have alternate text (alt text)
(MD045, no-alt-text)
142-142: Images should have alternate text (alt text)
(MD045, no-alt-text)
264-264: Images should have alternate text (alt text)
(MD045, no-alt-text)
272-272: Images should have alternate text (alt text)
(MD045, no-alt-text)
283-283: Images should have alternate text (alt text)
(MD045, no-alt-text)
290-290: Images should have alternate text (alt text)
(MD045, no-alt-text)
⏰ 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: Check PR Checklist Resolution
- GitHub Check: Pre-commit Check
🔇 Additional comments (1)
docs/source/blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.md (1)
250-252: Wording LGTM — upstream issue/PR statuses verified; qualify with "as of September 20, 2025".
- pytorch/pytorch#163061 — open (torch.compile kernels called with GIL held; deadlock risk with CUDA hostfunc callbacks).
- pytorch/pytorch#163062 — open (implicit/synced D2H copy performed with the GIL held).
- NVIDIA/TensorRT-LLM PR #7871 — open (created/edited Sep 19, 2025; disables torch.compile for CapturableGuidedDecoder; references pytorch#163061).
- NVIDIA/TensorRT-LLM PR #6948 — merged Sep 3, 2025 (adds CapturableGuidedDecoder and enables GIL releases in some C++ bindings).
Add "as of September 20, 2025" to the paragraph (docs/source/blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.md lines 250–252) or update the links/statuses just before publishing.
|
PR_Github #19389 [ skip ] triggered by Bot |
|
PR_Github #19389 [ skip ] completed with state |
juney-nvidia
approved these changes
Sep 20, 2025
MrGeva
pushed a commit
to nv-auto-deploy/TensorRT-LLM
that referenced
this pull request
Sep 21, 2025
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
nv-lschneider
pushed a commit
to nv-lschneider/TensorRT-LLM
that referenced
this pull request
Sep 22, 2025
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit
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
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
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.