[https://nvbugs/5374016][fix] improve error message #6893

QiJune · 2025-08-14T07:01:21Z

Summary by CodeRabbit

Bug Fixes
- Improved validation message when input sequences exceed the supported KV cache length. Users now receive a clear error explaining that the maximum KV cache length of the provided sequences is greater than the manager’s supported maximum, helping diagnose sequence length issues more quickly and accurately.

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.

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.

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

coderabbitai · 2025-08-14T07:01:28Z

📝 Walkthrough

Walkthrough

Introduces a dedicated error_message for an existing assertion in TrtllmAttentionWrapper.prepare, preserving the validation logic that the maximum KV cache length among input sequences does not exceed kv_cache_manager.max_seq_len. No public/exported signatures were changed.

Changes

Cohort / File(s)	Summary
Attention backend validation `tensorrt_llm/_torch/attention_backend/trtllm.py`	Refactors assertion to use a predefined error_message after copying host_kv_cache_block_offsets to kv_cache_block_offsets; validation logic remains unchanged and no public APIs are modified.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Suggested reviewers

Funatiq
StudyingShao
DanBlanaru

Tip

🔌 Remote MCP (Model Context Protocol) integration is now available!

Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats.

✨ 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.
- 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.
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 the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

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

CodeRabbit Commands (Invoked using PR/Issue comments)

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

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.

Status, Documentation and Community

Visit our Status Page to check the current availability of CodeRabbit.
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.

QiJune · 2025-08-14T07:02:54Z

/bot run

coderabbitai

Actionable comments posted: 0

🧹 Nitpick comments (1)

tensorrt_llm/_torch/attention_backend/trtllm.py (1)

767-774: Polish the error message and avoid recomputing max; use Python ints for readability

Two small improvements:

Convert 0-d tensors to Python ints to avoid printing "tensor(..., dtype=...)" in the error string.
Avoid recomputing max() twice.

Apply this diff:

-            error_message = (
-                f"The max KV cache length of input sequences ({self.kv_lens[:self.num_seqs].max()}) "
-                f"exceeds the KV cache manager's maximum supported length "
-                f"({self.kv_cache_manager.max_seq_len}).")
-
-            assert self.kv_lens[:self.num_seqs].max(
-            ) <= self.kv_cache_manager.max_seq_len, error_message
+            max_kv_len = int(self.kv_lens[:self.num_seqs].max().item())
+            max_seq_len = int(self.kv_cache_manager.max_seq_len)
+            error_message = (
+                f"The max KV cache length of input sequences ({max_kv_len}) "
+                f"exceeds the KV cache manager's maximum supported length "
+                f"({max_seq_len})."
+            )
+            assert max_kv_len <= max_seq_len, error_message

Optional: If you want this to remain enforced even when Python is run with -O (asserts stripped), consider raising an exception instead:

-            assert max_kv_len <= max_seq_len, error_message
+            if max_kv_len > max_seq_len:
+                raise ValueError(error_message)

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 7ebb770 and 72b334e.

📒 Files selected for processing (1)

tensorrt_llm/_torch/attention_backend/trtllm.py (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

**/*.py

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else

Files:

tensorrt_llm/_torch/attention_backend/trtllm.py

**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

Prepend NVIDIA copyright header (current year) to all source files

Files:

tensorrt_llm/_torch/attention_backend/trtllm.py

tensorrt-cicd · 2025-08-14T07:08:45Z

PR_Github #15245 [ run ] triggered by Bot

QiJune · 2025-08-15T07:21:25Z

/bot run

tensorrt-cicd · 2025-08-15T07:26:28Z

PR_Github #15416 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-15T13:07:31Z

PR_Github #15416 [ run ] completed with state FAILURE
/LLM/release-1.0/L0_MergeRequest_PR pipeline #137 completed with status: 'FAILURE'

QiJune · 2025-08-18T01:58:24Z

/bot run

tensorrt-cicd · 2025-08-18T02:04:08Z

PR_Github #15565 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-18T05:47:40Z

PR_Github #15565 [ run ] completed with state SUCCESS
/LLM/release-1.0/L0_MergeRequest_PR pipeline #168 completed with status: 'SUCCESS'

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

improve error message

72b334e

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

QiJune requested a review from a team as a code owner August 14, 2025 07:01

QiJune requested a review from yuxianq August 14, 2025 07:01

QiJune changed the title ~~[https://nvbugspro.nvidia.com/bug/5374016][fix] improve error message~~ [https://nvbugs/5374016][fix] improve error message Aug 14, 2025

Merge branch 'release/1.0' into error_message

f751b56

coderabbitai bot reviewed Aug 14, 2025

View reviewed changes

yuxianq approved these changes Aug 14, 2025

View reviewed changes

Merge branch 'release/1.0' into error_message

613407e

QiJune requested review from MartinMarciniszyn, chzblych, juney-nvidia and litaotju August 18, 2025 09:17

litaotju approved these changes Aug 19, 2025

View reviewed changes

QiJune merged commit cd1b809 into NVIDIA:release/1.0 Aug 19, 2025
4 checks passed

yuanjingx87 pushed a commit that referenced this pull request Aug 20, 2025

[https://nvbugs/5374016][fix] improve error message (#6893)

fbf62db

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Aug 22, 2025

[https://nvbugs/5374016][fix] improve error message (NVIDIA#6893)

f3f6a88

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

joyang-nv pushed a commit that referenced this pull request Sep 1, 2025

[https://nvbugs/5374016][fix] improve error message (#6893)

ed4087a

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

[https://nvbugs/5374016][fix] improve error message #6893

[https://nvbugs/5374016][fix] improve error message #6893

Conversation

QiJune commented Aug 14, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitai bot commented Aug 14, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Suggested reviewers

Chat

Support

CodeRabbit Commands (Invoked using PR/Issue comments)

Other keywords and placeholders

Status, Documentation and Community

Uh oh!

QiJune commented Aug 14, 2025

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented Aug 14, 2025

Uh oh!

QiJune commented Aug 15, 2025

Uh oh!

tensorrt-cicd commented Aug 15, 2025

Uh oh!

tensorrt-cicd commented Aug 15, 2025

Uh oh!

QiJune commented Aug 18, 2025

Uh oh!

tensorrt-cicd commented Aug 18, 2025

Uh oh!

tensorrt-cicd commented Aug 18, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

QiJune commented Aug 14, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Aug 14, 2025 •

edited

Loading