Skip to content

[None][chore] add online help to build_wheel.py and fix a doc link#6391

Merged
zhenhuaw-me merged 4 commits intoNVIDIA:mainfrom
zhenhuaw-me:help-and-doc
Aug 4, 2025
Merged

[None][chore] add online help to build_wheel.py and fix a doc link#6391
zhenhuaw-me merged 4 commits intoNVIDIA:mainfrom
zhenhuaw-me:help-and-doc

Conversation

@zhenhuaw-me
Copy link
Member

@zhenhuaw-me zhenhuaw-me commented Jul 28, 2025

  • It's better to have some online help for build_wheel.py.
  • [chrome://tracing/](chrome://tracing/) will be turn into #chrome://tracing/. Need <chrome://tracing/>.

Summary by CodeRabbit

  • Documentation
    • Improved formatting of Chrome tracing tool URLs in performance analysis documentation for clearer presentation.
    • Enhanced command-line argument documentation by adding descriptive help messages to all build script options.

Description

Test Coverage

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.

Details

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 the stage-list parameter 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.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-pipeline

Reuse 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.

* It's better to have some online help for build_wheel.py.
* `[chrome://tracing/](chrome://tracing/)` will be turn into
  `#chrome://tracing/`. Need `<chrome://tracing/>`.

Signed-off-by: Zhenhua Wang <zhenhuaw@nvidia.com>
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jul 28, 2025

📝 Walkthrough

"""

Walkthrough

This update modifies documentation formatting for Chrome tracing tool URLs in the performance analysis guide and improves the command-line argument help messages in the build script. No functional code logic or public API changes were introduced.

Changes

Cohort / File(s) Change Summary
Documentation URL Formatting
docs/source/performance/perf-analysis.md
Changed Chrome tracing tool references from markdown link format to angle-bracketed URLs in two locations.
CLI Argument Help Descriptions
scripts/build_wheel.py
Added detailed help messages to all command-line arguments for clarity; reformatted argument definitions for readability. No logic changes.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Suggested labels

Documentation, Community want to contribute

Suggested reviewers

  • litaotju
  • hchings
  • nv-guomingz
    """

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.

✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

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
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai generate unit tests to generate unit tests for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@zhenhuaw-me
Copy link
Member Author

/bot run

@coderabbitai coderabbitai bot requested review from litaotju and nv-guomingz July 28, 2025 05:54
@coderabbitai coderabbitai bot added Community want to contribute PRs initiated from Community Doc <NV>TRTLLM's textual/illustrative materials: API refs, guides, tutorials. Improvement & clarity. labels Jul 28, 2025
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: 0

🧹 Nitpick comments (3)
scripts/build_wheel.py (3)

799-800: Wrap overly-long help string to satisfy Ruff E501.

Ruff flags this line as > 120 chars. Split it so the long example sits on a new line; this keeps the text readable without affecting behaviour.

-        "CUDA architectures to build for, will be passed to cmake `CUDA_ARCHITECTURES` variable. Example: `--cuda_architectures=90-real;100-real`"
+        (
+            "CUDA architectures to build for, forwarded to CMake `CUDA_ARCHITECTURES`.\n"
+            "Example: `--cuda_architectures=90-real;100-real`"
+        )

849-850: Same E501 issue here – break the sentence.

-        "Extra cmake variable definitions which can be specified multiple times. Example: -D \"key1=value1\" -D \"key2=value2\"",
+        (
+            "Extra CMake definitions (may be given multiple times).\n"
+            "Example:  -D \"key1=value1\"  -D \"key2=value2\""
+        ),

868-869: Long line > 120 chars – wrap for consistency.

-        "Directory containing internal_cutlass_kernels sources. If specified, the internal_cutlass_kernels and NVRTC wrapper libraries will be built from source."
+        (
+            "Path to internal_cutlass_kernels sources. When set, those kernels and the "
+            "NVRTC wrapper libraries are built from source."
+        )
📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 97f7e12 and 46c81e9.

📒 Files selected for processing (2)
  • docs/source/performance/perf-analysis.md (2 hunks)
  • scripts/build_wheel.py (3 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.py: Python code should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL).
Python constants should use upper snake_case (e.g., MY_CONSTANT).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a Python file, prefer docstrings over comments.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the docstring for the class.
Avoid using reflection in Python when functionality can be easily achieved without it.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.

Files:

  • scripts/build_wheel.py
**/*.{cpp,h,hpp,cc,cxx,cu,py}

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.

Files:

  • scripts/build_wheel.py
🪛 Ruff (0.12.2)
scripts/build_wheel.py

799-799: Line too long (146 > 120)

(E501)


849-849: Line too long (129 > 120)

(E501)


868-868: Line too long (162 > 120)

(E501)

🔇 Additional comments (3)
scripts/build_wheel.py (1)

784-795: Improved CLI usability – good addition.

Adding concise yet informative help= strings to these options will make the script far more discoverable for first-time users.
No behavioural impact detected, argument names & defaults remain unchanged.

docs/source/performance/perf-analysis.md (2)

55-56: Correct link formatting – looks good.

Switching to <chrome://tracing/> prevents Markdown from mangling the URL.


92-93: Consistent link fix applied here as well – ✅

The updated angle-bracket syntax renders correctly in all Markdown viewers.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13152 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13152 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9845 completed with status: 'FAILURE'

@coderabbitai coderabbitai bot requested a review from litaotju July 30, 2025 02:13
Copy link
Collaborator

@nv-guomingz nv-guomingz left a comment

Choose a reason for hiding this comment

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

LGTM

@zhenhuaw-me
Copy link
Member Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13460 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13460 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10076 completed with status: 'FAILURE'

@zhenhuaw-me
Copy link
Member Author

/bot help

@github-actions
Copy link

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.

Details

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 the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-pipeline

Reuse 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.

@zhenhuaw-me
Copy link
Member Author

/bot reuse-pipeline

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13508 [ reuse-pipeline ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13508 [ reuse-pipeline ] completed with state SUCCESS
Can't reuse PR_Github #13460 with status: FAILED

@zhenhuaw-me
Copy link
Member Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13544 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13544 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10152 completed with status: 'FAILURE'

@zhenhuaw-me
Copy link
Member Author

/bot run

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: 0

🧹 Nitpick comments (2)
scripts/build_wheel.py (2)

787-803: Excellent help text additions with one formatting issue.

The help descriptions are clear and informative. However, there's a line length violation that needs to be fixed.

Apply this diff to fix the line length violation:

     parser.add_argument(
         "--cuda_architectures",
         "-a",
-        help=
-        "CUDA architectures to build for, will be passed to cmake `CUDA_ARCHITECTURES` variable. Example: `--cuda_architectures=90-real;100-real`"
+        help="CUDA architectures to build for, will be passed to cmake "
+        "`CUDA_ARCHITECTURES` variable. Example: `--cuda_architectures=90-real;100-real`"

847-882: Comprehensive help text with formatting issues to address.

The help descriptions are thorough and include helpful examples. However, there are two line length violations that need fixing.

Apply this diff to fix the line length violations:

     parser.add_argument(
         "--extra-cmake-vars",
         "-D",
         action="append",
-        help=
-        "Extra cmake variable definitions which can be specified multiple times. Example: -D \"key1=value1\" -D \"key2=value2\"",
+        help="Extra cmake variable definitions which can be specified multiple times. "
+        "Example: -D \"key1=value1\" -D \"key2=value2\"",
         default=[])
     parser.add_argument(
         "--internal-cutlass-kernels-root",
         default="",
-        help=
-        "Directory containing internal_cutlass_kernels sources. If specified, the internal_cutlass_kernels and NVRTC wrapper libraries will be built from source."
+        help="Directory containing internal_cutlass_kernels sources. "
+        "If specified, the internal_cutlass_kernels and NVRTC wrapper libraries will be built from source."
📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between b9dea18 and 8a13829.

📒 Files selected for processing (1)
  • scripts/build_wheel.py (3 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.py: Python code should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile = ...).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL = ...).
Python constants should use upper snake_case (e.g., MY_CONSTANT = ...).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a Python file, prefer docstrings over comments.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the docstring for the class.
Avoid using reflection in Python when functionality can be easily achieved without it.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.

Files:

  • scripts/build_wheel.py
**/*.{cpp,h,hpp,cc,cxx,cu,py}

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. The block should be prepended to the top of all files, including .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.

Files:

  • scripts/build_wheel.py
🪛 Ruff (0.12.2)
scripts/build_wheel.py

802-802: Line too long (146 > 120)

(E501)


852-852: Line too long (129 > 120)

(E501)


871-871: Line too long (162 > 120)

(E501)

🔇 Additional comments (3)
scripts/build_wheel.py (3)

804-841: LGTM! Clear and concise help descriptions.

The help text additions for build control arguments are well-written and accurately describe the functionality.


883-924: LGTM! Excellent coverage of specialized build options.

The help text for all specialized feature arguments is clear, concise, and accurately describes each option's purpose.


786-924: Excellent documentation enhancement effort!

This comprehensive addition of help text to the build script significantly improves developer experience by providing clear guidance on all available options. The descriptions are accurate, informative, and include helpful examples where appropriate.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #13769 [ run ] triggered by Bot

@zhenhuaw-me zhenhuaw-me changed the title chore: add online help to build_wheel.py and fix a doc link [None][chore] add online help to build_wheel.py and fix a doc link Aug 1, 2025
@tensorrt-cicd
Copy link
Collaborator

PR_Github #13769 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10350 completed with status: 'SUCCESS'

@zhenhuaw-me zhenhuaw-me merged commit 59d91b8 into NVIDIA:main Aug 4, 2025
4 of 5 checks passed
@zhenhuaw-me zhenhuaw-me deleted the help-and-doc branch August 4, 2025 05:14
lancelly pushed a commit to lancelly/TensorRT-LLM that referenced this pull request Aug 6, 2025
…VIDIA#6391)

Signed-off-by: Zhenhua Wang <zhenhuaw@nvidia.com>
Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
jain-ria pushed a commit to jain-ria/TensorRT-LLM that referenced this pull request Aug 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Community want to contribute PRs initiated from Community Doc <NV>TRTLLM's textual/illustrative materials: API refs, guides, tutorials. Improvement & clarity.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants